[IEEE-2018] Projects

Abstract:-" The correct timing is crucial for a robotics system that requires to expose a highly reliable behavior. Especially sincethe demand for robots, which are applied in collaborative environments, is increasing drastically, robots need to be even morereliable, and safe. In this paper, we propose a DSL to model the timing behavior of real-time sensitive componentbased roboticssystems. The DSL is integrated into the CoSiMA framework, which offers the ability to model, simulate, deploy, and analyze the(timing) behavior of robotics systems on different robotic platforms. In order to show the application of the DSL, we modeled andexecuted an experimental system using CoSiMA, which lets the humanoid robot COMAN perform a Zero Moment Point-basedwalk on a straight line, to eventually compare the actual execution with the model."

Abstract:-"The ability to sense the relative position of one’sown body parts is referred to as proprioception. This senseallows humans to interact with their environment without directobservation. Evolutionary Robotics is a field of study thatinvestigates the automatic development of robotic controllers andmorphologies. This paper proposes the idea of providing roboticcontrollers with a form of proprioception. This was achieved byproviding robotic controllers with simulated location informationduring execution.This study compared controllers with and without propriocep-tion, both in simulation and the real world. The controllers withproprioception outperformed those without, in all trials."

Abstract:-" Cloud robotics is a field of robotics that attempts to use Cloud technologies for robotics. The use of the Cloud forrobotics and automation brings some potential benefits largely ameliorating the performance of robotic systems. However, thereare also some challenges. First of all, from the viewpoint of architecture, how to model and describe the architectures of Cloudrobotic systems? How to deploy the architecture in Cloud? Our proposed approach in this paper is based on the principles ofsoftware architectures. In particular, we leverage our lightweight architectural solution to solve the architecture problem of Cloudrobotics and discuss different solutions to deploy Cloud robotics system in Cloud."

Abstract:-"- This paper suggests an artificial neural network approach to an object locator and picker. A robotic arm with two joints and a rotating base will function as a pick-and-placemachine. The system follows the following constraints: (1) thebase of the robotic arm will be situated at a predetermined andfixed position, hence limiting the area at which it can locate andpick an object and; (2) the object will be placed on a flat surface.The span of the robotic arm will determine this area. Also, itshould be noted that the arm's base and joints can move forlimited angles only. The area of interest by the arm will bemapped into grids with coordinates. The inputs to the artificialneural network system will be the coordinates at which the objectwas positioned. Its outputs will be the angles of each joint of therobotic arm such that it can pick the object at its correspondingposition.Index Terms- artificial neural networks, robotic arm, pick-and-place"

Abstract:-" Hand gesture control system has been unfolding the entire humanity to quite a wide range of applications, such as human android interaction, automation & control, virtualgames, 3D animations, posture recognition language, trafficsignal controlling, virtual play station, etc. This glove can be usedto control small scale machines and home appliances. Increasedusage of robots in unfavorable cases where conditions don’t staycertain like rescue operations and nuclear environment has madeadvancement in the modern world of army and defense. Thiswork proposes an integrated approach of tracking andrecognition of hands which is intended to be used as human-robot interaction interface (inferred from HMI (human machineinterface)).Keywords - Arduino UNO, Arduino DUE, Accelerometer, FlexSensors, Electromagnetic Pulse Gun(EMP), Human MachineInterface(HMI)"

Abstract:-" Robotic hand-arm is used in many areas ranging from household to commercial purposes. In the last decade, there has been a rapid growth in the applications of the roboticarm with gripper involving exploration of an area and thenperforming a specified task. Currently different varieties ofrobotic arms are available for commercial use with theirrespective technical applications. This paper provides a newtechnical insight into the area of robotic arm. The proposed workmakes improvements over the existing methods by designing arobotic arm with 7 DOF (Degree of Freedom), and then startsworking at arm envelope, space and increasing its efficiency.Finally, we add grip, hold and place capability using differentalgorithms and simulation. The proposed approach involving arobotic arm with 7 DOF outperforms the traditional methods ofdesigning a robotic arm.Keywords— Robotic arm, Gripper, Axis, Degree of freedom(DOF)."

Abstract:-"The importance of STEM (Science, Technology,Engineering and Mathematics) education is globally acknowledged and encouraged. The problem is the lack ofinterest, of school learners to participate in these subjects. Howto create an enjoyable, interactive yet educational journey thatencourages these ideals is the focus of this article? A line isdraw between the US educations system and challenges whichalso stand out in the South African context.A question posed; are children equipped with problemsolving and analytical thinking skills that are more resilient inthe changing job market?The vision should be a future of young ""Digital Makers"",and not only digital consumers!Keywords- problem solving, robotics, programming skills,educator training, Digital Makers, STEM, Blockley."

Abstract:-"Using a pressurized waterjet for cutting or abrasing tissue is a well established method in surgery. This paper presents a robotic tool for minimally invasive waterjet surgery with twodegrees of freedom, integrated suction and an optional splashprotection. The function of the tool and the effect of the splashprotection on the suction of the applicated water was successfullyevaluated in tests with ballistic gelatine. Based on this evaluateddesign, a concept for further increasing the oscillation frequencyof the instrument tip is introduced and the results of preliminarytests of a simplified mockup are shown.Index Terms—Medical robotics, instrument, waterjet, surgery"

Abstract:-"Ankle passive exoskeleton has been demonstratedto enhance walking economy and reduce the metabolic costduring walking. How to develop multi-articular passiveexoskeleton to further reduce the metabolic cost during humanwalking still remains a challenge. In this paper, we develop ahip-knee passive exoskeleton that uses springs to assist both hipextension and knee flexion. Springs in the exoskeleton are firstlystretched to store some of the negative mechanical power ofknee joint during the late swing phase, then the stored energy inthe springs is released to assist hip extension during the earlystance phase. The whole process is controlled by a mechanicalclutch. The experiment results show that the metabolic cost wasreduced by 7.6% compared to walking without the exoskeleton.To our knowledge, this is the first multi-articular passiveexoskeleton that can reduce the metabolic cost of walking. Thispaper also discusses the possibility for the passive exoskeleton toexploit heel-strike energy for further reducing the metaboliccost of walking."

Abstract:-" The design of an assistive robot for people with partially impaired walking ability demands unique requirements, such as minimal mechanical impedance and high back-drivability, as well as high power density. Mechanical partsmust be ergonomically designed, such that users can use thedevices for a long period of time without discomfort. Themotor control function of the incomplete paraplegics is notas robust as that of the normal, and thus the overall humanbody system becomes vulnerable to disturbances (i.e., externalforces, inclinations, etc.) or model variations (i.e., loads, etc.).It is, however, still active, unlike complete paraplegic patients,and thus the robot must not generate any unexpected resistanceto the voluntary motions of the incomplete paraplegics forthe sake of minimal discomfort. This paper introduces a newwearable robot, called Angel-suit, particularly developed forassisting such people with partially impaired walking ability.The transparent assistance is achieved by series-elastic actua-tion mechanism. A case study of Angel-suit for a 11-years-oldfemale patient with spina bifida is also briefly introduced inthis paper."

Abstract:-" Soft robots which employ materials with inherent compliance have demonstrated great potential in a variety ofapplications such as manipulators, medical tools and wearabledevices. This paper presents an origami-folding inspired designand fabrication approach for developing semi-soft robotic arms.The approach starts from a conceptual design by identifyingfoldable origami structures. This is followed by the kinematicmodelling of the selected origami skeleton with base folds ofthick panels and flexible hinges. The final step realizes thedesign by 3D printing the skeleton and laminating the skeletonto flexible membranes on a heated vacuum table. Followingthe proposed approach, a foldable origami tube structure isdesigned, modelled and used as the exoskeleton for a pneumaticsemi-soft robotic arm. Prototypes are developed by laminatinga pair of 3D printed thermoplastic polyurethane (TPU) origamiskeleton structures with TPU fabric film. The soft arm isactuated by a vacuum pump and its performances is evaluatedthrough quasi-static tests. Experimental results show that thesoft robotic arm achieves a maximum contraction ratio of47.53% providing 23.463 N axial tension force when applyinga regulated negative pressure of −1 bar. Two extensible andfoldable pneumatic arms are integrated on a micro aerialvehicle (MAV) to obtain a platform with the potential of aerialmanipulation capabilities in confined and hard to reach areas."

Abstract:-" Coral reefs are declining worldwide. Yet, critical information remains unknown about the basic biological, ecological, and chemical processes that sustain coral reefsbecause of the challenges to access their narrow crevices andpassageways. A robot that grows through its environment wouldbe well suited to this challenge as there is no relative motionbetween the exterior of the robot and its surroundings. In thiswork, we design and develop an eversion robot for operationunderwater, show that existing models work for constrainedpassageways if external contacts are taken into account, andpresent a new model to describe the forces on the robot duringretraction. We use ambient water to pressurize the robot andmaintain a neutral buoyancy. The robot operates in openloop without any steering, but can rely on its compliance toconform to natural crevices and pathways in its environment.We demonstrate the mechanism of eversion and retraction foran underwater soft robot as a potential approach for futurenon-destructive exploration of coral reefs."

Abstract:-" In this paper we present Skinflow, a novel soft robotic sensor based on liquid transmission. The sensor com-bines liquid filled soft silicone chambers and optical sensors tomeasure pressure, bending and vibration. When mechanicallystimulated, the volume of the chambers changes and thischange is transmitted to a display cell by an incompressible,coloured liquid. The displacement of the liquid in the channelsis captured by a CCD camera and is quantified by imageprocessing algorithms. We present three implementations ofthis concept. The first device is a soft button array with fourpressure sensitive buttons. The second implementation is athree-dimensional soft touchpad, that consists of two sensorlayers oriented at 90◦to each other. Both layers have eightmacrochannels that are filled with coloured liquid. The sensoris able to measure the position and the intensity of the touch.Finally, the third device shows how the processing unit forthe proposed liquid filled sensors can be integrated using asmart vision camera and a microcontroller. Three soft bendsensors are connected to the processing unit and we controlthe brightness of three light emitting diodes (LEDs) in real-time by bending them. The presented sensors are safe, lowcost and scalable. They can be used in soft robots, smarthomes and wearables as well as for medical diagnosis, especiallywhere electronic devices cannot be used due to electromagneticinterference (e.g. magnetic resonance imaging)."

Abstract:-" Soft robotic systems are composed of active and passively deformable structures which are intrinsically com-pliant, flexible, and elastic. Although these features offer ben-efits of adaptability, robustness, and safety, controlling thesetypes of robots is a significant challenge, in part from thedifficulty of obtaining feedback from sensors which providestate information without hindering the advantageous materialproperties which grant these systems their unique mechanicalbehavior. We demonstrate here the first integration of a flexible,stretchable, liquid metal-based strain sensor with vacuum-powered soft pneumatic actuators (V-SPAs) for simultaneouscontrolled feedback of the soft actuators as well as user inputand soft robotic device interaction. The soft sensors which areencapsulated within a Polydimethylsiloxane (PDMS) membraneare directly embedded in the outer body skin of the softactuators, and can be used to correlate the deformation ofthe body under vacuum actuation to overall actuator strainor to detect external disturbances. This information is used tocompute and control the angle of a rotational 3-DoF actuatormodule, as well as detect implicit user input control signalsby direct interaction without the need for an external controlinterface. The dual use of embedded sensing shown in thiswork provides a fundamental strategy for soft collaborativerobot applications.Index Terms— Soft pneumatic actuators, stretchable sensors,soft robotics"

Abstract:-" Pneumatically-actuated soft robots are limited by the need to provide a source of pressure, typically DC motor powered pumps, compromising the softness of the overallsystem. This has motivated the investigation of alternativemeans of providing pressure, including mono-propellant de-composition, combustion of hydrocarbons in oxygen, and activecomposite foams. In this work, we propose the thermally drivenevaporation of low-boiling point fluids as a facile method forproviding pressure to soft robotic systems. We first discuss andtest the thermodynamics of heating low-boiling point fluids. Wethen introduce two possible applications of low-boiling pointfluids in soft robotics. First, we demonstrate a cheap and easilyfabricated compliant heating element and show how this can beused to convert existing fluidic elastomer actuators to be drivenby low-boiling point fluids. Secondly, we also demonstrate andcharacterise a soft-matter pump driven by low-boiling pointfluids."

Abstract:-" Soft continuum manipulators exhibit promising applications over traditional rigid manipulators because of their compliant bodies. However, the unexpected phenomenon due tothe gravity, called instability, makes it challenging for design,modeling and control. In this paper, we design a two-sectionpneumatically actuated soft continuum manipulator, containingthree-chambered pneumatic actuators in each section andinvestigate the optimal Length to Diameter Ratio (LDR) of themanipulator by Finite Element Analysis (FEA). We introducea new measure variable — workspace ratio (WR) — toexamine the workspace as well as the instability and we candetermine our optimal LDR value based on this variable. Asoft manipulator is then fabricated and experimentally tested.The experimental results are in good agreement with modelsimulation. Results show the optimal value of LDR is atthe maximum LDR, which is about 4.71 for one-section softmanipulator and 3.91 for two-section soft manipulator. Thiscan be the guidance to the multiple-section soft manipulatordesign for further applications."

Abstract:-"Missions in extreme environments such as exploration and mapping of chemical leakage, radiation and high temperature are hazardous for human workers. Therefore,robotic solutions can be utilised in these applications. Swarmrobotics is an alternative approach to traditional robotics, withpotential to increase the efficiency of robotic solutions in anextreme environment. Swarm robotic systems are low-cost, robustand scalable. In this paper, we focused on an explorationscenario for use in an extreme environment application. Thescenario for this study was to explore the different levels ofradioactive or chemical leakage from drums in a nuclear storagefacility. The environment and mobile robot used for this work,Mona, were modelled in the V-REP simulation software. Theeffects of experimental parameters, i.e. the number of robotsand complexity of the storage facility, on the efficiency of theexploration system were evaluated. The results revealed that,an increase in population size increased the performance ofthe exploration significantly. Moreover, the complexity of theenvironment did not have significant impact on the performanceof the system.Index Terms—Swarm Robotics, Extreme Environment, Explo-ration, Collective Behaviour"

Abstract:-" A low-cost motor-less simple wearable mechanical arm support unit is presented as a viable alternative to todays assistive exoskeleton support units. By limiting the functionality of the device to stabilization rather than actuation, the cost couldsignificantly be reduced while still maintaining a wide range of applications. The basic idea is to let the device follow the wearersactions freely without obscuring the motion in normal mode, while fixating the arm at the desired angle and location when the userexpect to receive support; namely in lock mode. The lock-unlock mechanism is simple Bluetooth activated palm gesture of the non-operating arm while the support unit Bluetooth receiver stabilizes the arm at any desired angle or position in response to sensedgesture command. The lock-unlock mechanism is achieved by solely two solenoids, one at each of the joints; shoulder and elbow,with 3 Degree of Freedom (DoF) and 1 DoF respectively, leaving the wrist free to perform the desired hand operation andincreasing the precision of the locking mechanism."

Abstract:-" Cloud robotics is incessantly gaining ground, especially with the rapid expansion of wireless networks and Internet resources. In particular, computation offloading is emerging as a new trend, enabling robots with more powerful computationresources. It helps them to overcome the hardware and software limitations by leveraging parallel computing capabilities and theavailability of large amounts of resources in the cloud. However, the performance gain of computation offloading in cloud roboticsis still an ongoing research problem because of the conflicting factors that affect the performance. In this paper, we investigate thisissue and we design a distributed cloud robotic architecture for computation offloading based on Kafka middleware as messagingbroker. We experimentally validated our solution and tested its performance using image processing algorithms. Experimentalresults show a significant reduction in robot CPU load, as expected, with an increase in robot communication delays."

Abstract:-"–The paper deals with the information and computational models connected with solution of navigation and gravimetric tasks in underwater robotics. On the basis ofexperimental data, available probabilistic assessments of ac-curacy at trajectory measurements and mapping of gravityanomalies, informativity of an abnormal gravitation field aregiven with the aim of navigation by reconstructed gravimet-ric map.Key words: autonomous underwater robot (autonomousunmanned underwater vehicle), motion control, trajectorymeasurements, navigation, gravimetry, informativity."

Abstract:-" Robot-based neurorehabilitation strategies often ignore cognitive performance during treatment, but this is a need in populations dealing with a wide variety of cognitive andmotor impairments, such as the stroke and HIV populations,for which an association between the two have been established.In this study, we concurrently measure cognitive and motorperformance on a robotic cognitive-motor task and quantifycognitive-motor interference. We apply this method to a pilotgroup of healthy, stroke, and HIV-stroke subjects, and wedemonstrate the potential of smoothness and correct responserate as metrics to capture motor and cognitive-related dual-taskeffects."

Abstract:-" Lymphedema is a non-curative chronic swelling caused by impairment of the lymphatic system, affecting up to250 million patients worldwide. The patients suffer from lowquality of life because of discomfort and reduced range of motiondue to the swelling. Severe swellings can be immediatelymediated with special massaging technique known as theManual Lymphatic Drainage (MLD). Limitations of MLDinvolves long travel distances, the cost of regular treatmentsessions, and the lack of lymphedema specialists. Since MLD isperformed very gently, described as caressing a baby’s head, softwearable robotics with its inherent compliance and safety is theperfect solution to creating a light and safe wearablelymphedema massaging device. In this paper, origami-inspiredsoft fabric pneumatic actuator is developed that creates not onlynormal force, but also shear force which is essential in theperformance of MLD. The shear is created by the unfolding ofthe Z-shaped fold-lines as the actuator is inflated. One Z-foldedactuator module of 30 x 60 mm dimension with a single fold of15 mm fold height creates maximum shear force of about 1.5 Nand stroke displacement of about 30 mm when subjected tocompression loading of 5 N. The range of forces exerted can betuned by varying the tension of the compressive clothingcovering the actuators, and the stroke displacement can bevaried by changing the parameter of the actuator module itself,such as the fold height and the number of the folds. The modulescan also be repeatedly actuated under compressive clothing, andtherefore, the developed actuator modules have high potential asa wearable massaging device."

Abstract:-"Image caption generation is a task that generates asentence from a raw image, which is mimicking the intelligenceof human that can acquire knowledge from the view. Thedifficulty of this task is the combination of multimodalknowledge learning, i.e. recognition of objects, actions, scenes,human, etc. In order to perform semantic understanding forservice robotics or other industrial applications, the caption mustbe enhanced for recognition of the objects in the confinedenvironment. We propose a template-based augmentationmethod for improving the capability of object recognition whileretaining the other capability of the image caption model. Thiswork opens a new era of image caption generation trainingprocedure that the caption dataset and the classification datasetcan be combined to train the deep captioning model. We show inour experiments that our improved model outperforms theoriginal model in SPICE metrics by 4 times.Keywords—machine learning, image captioning, objectrecognition, service robot"

Abstract:-" - Robot programming usually consists of four steps:(1) task planning; (2) task sequencing; (3) path planning and (4)motion planning. Task (2) and (3-4) are strongly coupled. Forexample, the optimal robot path, which is function of the robotkinematics, relies on the pre-defined schedule of tasks, whosesequencing is computed based on the assumption that thetravelling “cost” from one task to the next is only driven by theEuclidean distance in Cartesian space. Current methods tendsto decouple the problem and sequentially compute the tasksequencing in the T-space, and then compute the robot path bysolving the inverse kinematics in the C-space. However, thoseapproaches suffer the capability to reach a global optimum. Thispaper aims at developing a novel approach which integratessome of the key computational requirements of the pathplanning in the early stage of the task sequencing. Multi-attribute objectives are introduced to take into account: robotpose and reachability, data quality, obstacles avoidance, overallcycle time. The paper introduces a novel multi-attributeapproach to find the optimized task sequencing via candidateposes solving inverse kinematics in the T-space. This is based onthe core idea to combine T-space and C-space. The proposedsolution has been tested on a vision-based inspection robotsystem with application to automotive body assembly systems.Results could however impact a wider area, from navigationsystems, game and graph theory, to autonomous drivingsystems.Keywords - Robotic task sequencing, TSPN, Robot visionsystem, Multi-attribute Optimization"

Abstract:-" In autonomous driving community, numerousbenchmarks have been established to assist the tasks of 3D/2Dobject detection, stereo vision, semantic/instance segmentation.However, the more meaningful dynamic evolution of the sur-rounding objects of ego-vehicle is rarely exploited, and lacksa large-scale dataset platform. To address this, we introduceBLVD, a large-scale 5D semantics benchmark which doesnot concentrate on the static detection or semantic/instancesegmentation tasks tackled adequately before. Instead, BLVDaims to provide a platform for the tasks of dynamic 4D(3D+temporal) tracking, 5D (4D+interactive) interactive eventrecognition and intention prediction. This benchmark will boostthe deeper understanding of traffic scenes than ever before.We totally yield 249, 129 3D annotations, 4, 902 independentindividuals for tracking with the length of overall 214, 922points, 6, 004 valid fragments for 5D interactive event recogni-tion, and 4, 900 individuals for 5D intention prediction. Thesetasks are contained in four kinds of scenarios depending onthe object density (low and high) and light conditions (daytimeand nighttime). The benchmark can be downloaded from ourproject site https://github.com/VCCIV/BLVD/."

Abstract:-" Inherent compliance plays an enabling role insoft robots, which rely on it to mechanically conform to theenvironment. However, it also limits the payload of the robots.Various variable stiffness approaches have been adopted tolimit compliance and provide structural stability, but mostof them can only achieve stiffening of discrete fixed regionswhich means compliance cannot be precisely adjusted fordifferent needs. This paper offers an approach to enhance thepayload with finely adjusted compliance for different needs.We have developed a manipulator that incorporates a novelvariable stiffness mechanism and a sliding layer mechanism.The variable stiffness mechanism can achieve a 6.4 stiffnesschanging ratio with a miniaturized size (10mm diameter forthe testing prototype) through interlocking jamming layers witha honeycomb core. The sliding layer mechanism can activelyshift the position of the stiffening regions through sliding ofjamming layers. A model to predict the robot shape is derivedwith verifications via an experiment. The stiffening capacity ofthe variable stiffness mechanism is also empirically evaluated.A case study of a potential application in laparoscopic surgeriesis showcased. The payload of the manipulator is investigated,and the prototype shows up to 57.8 percentage decrease of thevertical deflection due to an external load after reconfigurations."

Abstract:-" Using the effects of quantum mechanics for computing challenges has been an often discussed topic for decades. Thefrequent successes and early products in this area, which we have seen in recent years, indicate that we are currently entering anew era of computing. This paradigm shift will also impact the work of robotic scientists and the applications of robotics. Newpossibilities as well as new approaches to known problems will enable the creation of even more powerful and intelligent robotsthat make use of quantum computing cloud services or co-processors. In this position paper, we discuss potential application areasand also point out open research topics in quantum computing for robotics. We go into detail on the impact of quantum computingin artificial intelligence and machine learning, sensing and perception, kinematics as well as system diagnosis. For each topic wepoint out where quantum computing could be applied based on results from current research."

Abstract:-" Robotic-Assisted Minimally Invasive Surgery allows for easy recording of kinematic data, and presents excellentopportunities for data-intensive approaches to assessment of surgical skill, system design, and automation of procedures. However,typical surgical cases result in long data streams, and therefore, automated segmentation into gestures is important. The publicrelease of the JIGSAWS dataset allowed for developing and benchmarking data-intensive segmentation algorithms. However, thisdataset is small and the gestures are similar in their structure and directions. This may limit the generalization of the algorithms toreal surgical data that are characterized by movements in arbitrary directions. In this paper, we use a recurrent neural network tosegment a suturing task, and demonstrate one such generalization problem-limited generalization to rotation. We propose a simpleaugmentation that can solve this problem without collecting new data, and demonstrate its benefit using: (1) the JIGSAWS dataset,and (2) a new dataset that we recorded with a da Vinci Research Kit. Our study highlights the prospect of using data augmentationin the analysis of kinematic data in surgical data science."

Abstract:-" This paper introduces the KUKA Robot LearningLab at KIT – a remotely accessible robotics testbed. Themotivation behind the laboratory is to make state-of-the-artindustrial lightweight robots more accessible for education andresearch. Such expensive hardware is usually not available tostudents or less privileged researchers to conduct experiments.This paper describes the design and operation of the RobotLearning Lab and discusses the challenges that one faces whenmaking experimental robot cells remotely accessible. Especiallysafety and security must be ensured, while giving users as muchfreedom as possible when developing programs to control therobots. A fully automated and efficient processing pipeline forexperiments makes the lab suitable for a large amount of usersand allows a high usage rate of the robots."

Abstract:-" Humanoid robots typically display locomotionpatterns that include walking with flat foot-ground contact, andknees slightly bent. However, analysis of human gait indicatethat several physiological mechanisms like stretched knees, heel-strike and toe push-off increase the step length and energeticefficiency of locomotion. This paper presents an implementationof two of those mechanisms, namely stretched knees and push-off, on a quasi-static whole-body balancing controller. Theinfluence of such mechanisms on the kinematic capabilitiesof the DLR humanoid robot TORO is analyzed in differentexperiments, and their benefits are thoroughly discussed. As aresult, the energetic savings of balancing with stretched kneesare shown to be of reduced magnitude with respect to the overallpower consumption of the robot, and the ability of TORO fornegotiating stairs is greatly enhanced."

Abstract:-"Perforations in flexible endoscopy arelife-threatening. Defect closure or suturing in flexible endoscopyhas long been a critical challenge due to the confined space ofthe access routes and surgical sites, high dexterity and forcedemands of suturing tasks, as well as critical size and strengthrequirements of wound closure. This paper introduces a novelrobotic suturing system for flexible endoscopic surgery. Thissystem features a flexible, through-the-scope,five-degree-of-freedom robotic suturing instrument. Thisinstrument allows the surgeon to endoscopically manipulate aneedle via a master console to create running stitches and knotsin flexible endoscopy, which is not possible with existing devices.Successful ex-vivo trials were conducted inside porcine colons toshow how surgical stitches and knots can be endoscopicallycreated and secured in a completely new way. This newtechnology will change the way how surgeons close defects orperforations in flexible endoscopic surgery."

Abstract:-" In this paper the first robot-based prototype ofa semi-autonomous upper-limb exoprosthesis is introduced,unifying exoskeletons and prostheses [1]. A central goal ofthis work is to minimize unnecessary interaction forces onthe residual limb by compensating gravity effects via a upperbody grounded exoskeleton. Furthermore, the exoskeleton pro-vides the residual limb’s kinematic data that allows to designmore intelligent coordinated control concepts. The soft-roboticsdesign of a prototype consisting of a transhumeral prosthesisand a robot-based exoskeleton substitute is outlined. For thisclass of hybrid systems a human embodied dynamics modeland semi-autonomous coordinated motion strategies are derived.Here, in contrast to established standard sequential strategies alljoints are moved simultaneously according to a desired task. Incombination with an app-based programming framework thestrategy goals are set either user-based via kinesthetic teachingor autonomously via 3D visual perception. This enables the userto execute tasks faster and more intuitive. First experimentalevaluations show promising performance with a healthy subject."

Abstract:-"The use of industrial robots in modern manufacturingscenarios is a rising trend in the engineering industry. Currently,industrial robots are able to perform pre-programmed tasksvery efficiently irrespective of time and complexity. However,often robots encounter unknown scenarios and to solve those,they need to cooperate with humans, leading to unnecessarydowntime of the machine and the need for human intervention.The main aim of this study is to propose a method to developadaptive industrial robots using Machine Learning (ML)/Machine Vision (MV) tools. The proposed method aims toreduce the effort of re-programming and enable self-learning inindustrial robots. The elaborated online programming methodcan lead to fully automated industrial robotic cells inaccordance with the human-robot collaboration standard andprovide multiple usage options of this approach in themanufacturing industry. Machine Vision (MV) tools used foronline programming allow industrial robots to makeautonomous decisions during sorting or assembling operationsbased on the color and/or shape of the test object. The test setupconsisted of an industrial robot cell, cameras and LIDARconnected to MATLAB through a Robot Operation System(ROS). The online programming tests and simulations wereperformed using Virtual/Augmented Reality (VR/AR) toolkitstogether with a Digital Twin (DT) concept, to test the industrialrobot program on a digital object before executing it on the realobject, thus creating a safe and secure test environment."

Abstract:-" Soft robotic systems are composed of active andpassively deformable structures which are intrinsically com-pliant, flexible, and elastic. Although these features offer ben-efits of adaptability, robustness, and safety, controlling thesetypes of robots is a significant challenge, in part from thedifficulty of obtaining feedback from sensors which providestate information without hindering the advantageous materialproperties which grant these systems their unique mechanicalbehavior. We demonstrate here the first integration of a flexible,stretchable, liquid metal-based strain sensor with vacuum-powered soft pneumatic actuators (V-SPAs) for simultaneouscontrolled feedback of the soft actuators as well as user inputand soft robotic device interaction. The soft sensors which areencapsulated within a Polydimethylsiloxane (PDMS) membraneare directly embedded in the outer body skin of the softactuators, and can be used to correlate the deformation ofthe body under vacuum actuation to overall actuator strainor to detect external disturbances. This information is used tocompute and control the angle of a rotational 3-DoF actuatormodule, as well as detect implicit user input control signalsby direct interaction without the need for an external controlinterface. The dual use of embedded sensing shown in thiswork provides a fundamental strategy for soft collaborativerobot applications.Index Terms— Soft pneumatic actuators, stretchable sensors,soft robotics"

Abstract:-"KEYWORDS Knowledge sharing, Knowledge evolution, Industrial cloud robotics, Iterative updating Industrial Cloud Robotics (ICR), with the characteristics of resource sharing, lower cost and convenient access, etc., can realize the knowledge interaction and coordination among cloud Robotics (CR) through the knowledge sharing mechanism. However, the current researches mainly focus onthe knowledge sharing of service-oriented robots and theknowledge updating of a single robot. The interaction andcollaboration among robots in a cloud environment still havechallenges, such as the improper updating of knowledge, theinconvenience of online data processing and the inflexibility ofsharing mechanism. In addition, the industrial robot (IR) alsolacks a well-developed knowledge management framework inorder to facilitate the knowledge evolution of industrial robots.In this paper, a knowledge evolution mechanism of ICR basedon the approach of knowledge acquisition - interactive sharing- iterative updating is established, and a novel architecture ofICR knowledge sharing is also developed. Moreover, thesemantic knowledge in the robot system can encapsulateknowledge of manufacturing tasks, robot model and schemedecision into the cloud manufacturing process. As newmanufacturing tasks arrived, the robot platform downloadstask-oriented knowledge models from the cloud serviceplatform, and then selects the optimal service composition andupdates the cloud knowledge by simulation iterations. Finally,the feasibility and effectiveness of the proposed architectureand approaches are demonstrated through the case studies."

Abstract:-This presents a preliminary evaluation of the usability of a novel system for cognitive testing, which is based on the multimodal interfaces of the social robot “Pepper” and the IBM cloud AI “Watson”. Thirty-six participants experienced the system without assistance and filled the System Usability Scale questionnaire. Results show that the usability of the system is highly reliable. Keywords—Social Robot, Cognitive Assessment, IBM Watson

Abstract:-This live demonstration presents an audio-guided neuromorphic robot: from a Neuromorphic Auditory Sensor (NAS) to locomotion using Spiking Central Pattern Generators (sCPGs). Several gaits are generated by sCPGs implemented on a SpiNNaker board. The output of these sCPGs is sent in a real-time manner to an Field Programmable Gate Array (FPGA) board using an AER-to-SpiNN interface. The control of the hexapod robot joints is performed by the FPGA board. The robot behavior can be changed in real-time by means of the NAS. The audio information is sent to the SpiNNaker board which classifies it using a Spiking Neural Network (SNN). Thus, the input sound will activate a specific gait pattern which will eventually modify the behavior of the robot. Index Terms—Neuromorphic Auditory Sensor, Spiking Central Pattern Generator, Neurorobotics, SpiNNaker, AddressEvent-Representation

Abstract:- The Mechatronic Engineer José Cornejo presented in his Undergraduate Thesis at Ricardo Palma University, the design of a surgical system prototype, which has an anthropomorphic robotic arm with 5 degrees of freedom called Biomedik Surgeon, used in simulation to research in the field of Biomedical Engineering, with the purpose of training the surgical skills in medical students using concepts of Medical Robotics, and in this way prepare the future physicians of Peru to offer advanced technology care in Surgery. The term Surgical Engineering was introduced, which is an area that involves the multidisciplinary work among engineers, architects and health professionals in the path of creating technologies to provide high quality care for the surgical patient and to improve the attention processes in Surgical Centers in Peru. The medical description of the Surgical Robotic System was deepened, where criteria of mechanical, electronic, electrical and software control were applied to build a prototype based on international standards of advanced technologies used in the area of surgery. Finally, the training and simulation tests in Minimally Invasive Surgery techniques were performed with the use of a cutting tool. The successful accreditation of the project was granted by the Scientific Society of Medical Students at the Faculty of Human Medicine “Manuel Huamán Guerrero” - Ricardo Palma University. Keywords— Biomedik Surgeon, Biomedical Engineering, Medical Students, Faculty of Human Medicine, Medical Robotics, Surgical Engineering, Surgical Robotic System, Minimally Invasive Surgery

Abstract:-Inchworm, a kind of caterpillar, traverses various terrains by moving its center of mass (COM) with simple twoanchor crawling locomotion. Because of this advantage, many soft locomotion robots were developed to mimic this inchwormlike two-anchor crawling. However, most of these developed inchworm robots have difficulties in moving its COM in the vertical height direction, so these robots face difficulties in overcoming discrete high terrain, like stairs. In this paper, we propose a flexible sheet-based inchworm robot (Loco-sheet) that employs a novel locomotion mode made by morphing to overcome discrete high terrains, like stairs. In this novel mode, called the S-shape locomotion mode, the robot changes its body shape into an ‘S’ to lift the COM up, by exploiting bending stiffness of the flexible sheet to climb stairs. The bending stiffness of the sheet was designed to be sufficient to lift up the COM. The robot also does two-anchor crawling, called the omega-shape locomotion mode, to pass through low gaps. Loco-sheet is designed with anisotropic friction wheels and a mass distribution advantageous for omega-shaped locomotion without slippage. Morphing between two modes is reversible. Motor-tendon driven actuation system allows the robot to pull the far end of the sheet from the actuator to fold the body, and allows the robot to operate untethered from an external power supply with small volume actuators. The robot climbs a 90 mm stair, passes through 72 mm low gaps, and travels flat surfaces. Therefore, Loco-sheet is suitable for traveling a variety of undefined environments. Index Terms—Soft locomotion robot, Multi-modal locomotion robot, Inchworm robot, Morphing robot, Flexible sheet-based robo

Abstract:-Pneumatic driven soft robotic gripper has been studied intensively in recent years for grasping various types of objects including food materials. However, grasping of finely chopped and granular food materials has not been investigated frequently. This paper presents a pneumatic soft gripper capable of forming an approximately closed cavity to wrap the chapped and granular food materials. The gripper consists of four soft fingers and each finger was constructed by multiple horizontal and vertical air chambers. When the chambers were inflated, the finger bends towards two perpendicular directions. Finite element (FE) model of the soft finger was developed to predict the desired deformation behaviors. A robotic gripper was assembled with four soft fingers in a circular configuration. Experimental tests were conducted on grasping granular kernel corn, chopped green onion, and boiled hijiki. Results showed thattheproposedgripperisabletowrapthefoodmaterialsand the averaged weight of the grasped materials can be controlled by varying the insertion depth. However, the variations in grasped weight among trials are relatively large.

Abstract:-Various soft grippers based on the soft pneumatic actuators (SPAs) have been studied actively since it offers pliable bending motion, inherent compliance, and a simple morphological structure. For improved functionality or feedback control, embedding sensors to SPAs has also been studied vigorously. However, evaluating grasping quality of the gripper with the embedded sensor has rarely been studied even if the stable grasping is significant in robotic manipulation. Thus, in this study, we developed a sensorized hybrid gripper which embeds a commercial bending sensor and a customized tactile sensor, and the grasping quality based on the largest-minimum wrench (LMW), which evaluate the contact wrenches, was calculated. Thegraspingqualitymetrics withtwo differentgrips were compared experimentally.

Abstract:-In the field of soft robotics, the material selection plays an important role and markedly influences the properties of the actuators. More complex actuators can be manufactured by combining the strengths of multiple materials in a single design. To allow this, a good connection between the different materials is indispensable. Making a physical connection between flexible materials, having different properties, is difficult and leads to failure and damage due to stress concentrations at the interface. This is why in soft robots, most of the time single-material actuators are used. In this work, re-mendable elastomeric polymers are used to construct multi-material soft actuators. These Diels-Alder polymers consist of a thermoreversible covalent network that allows chemical bonding at the interface between two parts. Two Diels-Alder polymers were synthesised with contrasting mechanical properties. Although, having dissimilar Young’s moduli, these different materials can chemically bind at the interface, resulting in a very strong connection. This principle was elaborated in a dual-material tendon-driven soft gripper. Additionally, the reversible network allows to heal damages using mild heating. This healing ability was demonstrated by subsequently damaging and completely healing the dual-material soft actuator multiple times. Index Terms—Soft Robot Materials and Design, Self-Healing Materials, Diels-Alder polymers, Smart Materials.

Abstract:- Rehabilitation interventions play a vital role especially in most post-stroke care. Many rehabilitation robotic devices have been designed and developed to assist many individuals suffering from stroke or similar disabling illness and living with reduced mobility of the arms, hands and other joint. However, these devices remain unmanageable to use by the patients alone not only because they are cumbersome to use but also due to their weights, fix and non-portable characteristics, and so on. Here for elbow joint rehabilitation, we investigate and propose a novel exoskeleton soft robotic arm, which is wearable, lightweight and portable so that it would allow patients to perform repetitive motion therapy more often with a greater intensity in their homes and relevant to their daily activities. The proposed arm consists of various novel pneumatic Muscle Actuators (pMA) capable of bending in contrary to traditional pMA. Analysis, design, integration and characterisation of the proposed arm are presented and geometrical and numerical models are obtained. Various experiments revealed its behaviour and the relationship among pressure, length, force, and bending angle in different setups such as isotonic and isometric. The nonlinear, time varying and intractable dynamic of the constructed prototype demanded the design and development of an appropriate closed loop controller for adhering to target rehabilitation profiles. As proof of the concept a Model Reference Adaptive Control (MRAC) was designed and results were presented. By achieving design objectives, this study shows that the proposed portable exoskeleton has the ability to offer more effective intense rehabilitation therapies at home without the need to therapists and with a lower cost. Keywords— upper extremity; limbs; rehabilitation; therapy;, soft robots; movement; motion; robot; elbow rehabilitation

Abstract:-Applied Academics is both a trend within pioneering educational institutions as well as a demand from the current generations of students at all levels. The first semesters of an engineering curricula focus on developing a solid theoretical basis in Mathematics, Physics and Programming before becoming immersed in practical projects. Therefore, first-year engineering students usually struggle to visualize the practical applications of their studies. Keywords— Student engagement, Applied Academics, competency-based education, active and collaborative learning, robotics, Educational Innovation, engineering skills

Abstract:-Rocker-bogie is kind of suspension system where wheels from each side of the vehicle are connected with a differential mechanismm. If the vehicle has not had turnable wheels and turns only using the velocity or heading differences of each side or the object, then increased taction on the most loaded wheels causes lifting of the swingarms in opposing directions. This article shows the way of active adjusting each wheel's body and threatens to fall over. Presented algorithm increases or decreases the angular velocity of selected wheels depending on the robot's rotation speed, acceleration, and traction. The algorithm is implemeted on an existing vehicle, and experimental part contains a comparision of behaviour with and without active control on different surfaces. keywods— Control, Algorithm, Robotics, Suspension

Abstract:-This paper describes the development and testing of the PlanetVac Xodiac sampler by Honeybee Robotics. This iteration of PlanetVac builds on Honeybee’s heritage of pneumatic sampling systems and modifies it to function on an Entry, Descent, and Landing (EDL) test bed vehicle. PlanetVac Xodiac was flown on Masten Space Systems Xodiac vehicle in the Mojave Desert of California. The sampler was designed to withstand the high temperatures emitted by the propulsion system plume, as well as the vibration and impact stresses of takeoff and landing. PlanetVac Xodiac not only survived all three end-to-end field tests, it also collected over three times the expected 100g sample in each trial.

Abstract:- Wearable robots for the legs have been developed for gait rehabilitation training and as assistive devices. Most devices have been rigid exoskeletons designed to substitute the function of users who are completely paralyzed. While effective for this target group, exoskeletons limit their users contributions to movements. Soft wearable robots have been suggested as an alternative that allows, and requires, active contributions from users with residual mobility.

Abstract:-Body weight support (BWS) system is widely used for patients to help their gait training. However, that existing systems require large workspace and elastic component in actuation makes the systems inappropriate for wide clinical use. The interactive treadmill was reported to be cost/space effectively simulate overground walking, but there was no suitable BWS system for the treadmill. We proposed a new concept of body weight support system for interactive treadmill. For wide clinical use, we applied a two-wire driven mechanism with simple actuator and a custom pelvic-type harness. With three healthy subjects, the performance of the proposed BWS system on unloading force control was evaluated, and the result showed that the feasibility of the proposed BWS system. Keywords— Gait training, body weight support, wire robots, interactive treadmill.

Abstract:-In this paper, a quadruped salamander-like robot with the capability of traversing complex terrain is developed, which presents not only leg joints used in traditional legged robots, but also spine joints, so as to increases its flexibility. To coordinate spine and leg joints to balance the robot’s center of gravity, a novel control method is proposed, which consists of an inverse kinematics-based control, a bio-inspired mechanism, and a coordination law. Specifically, the inverse kinematics is utilized to calculate the control for the legs, and biological inspiration is employed for the control of the spine, while the coordination between the legs and the spine is ensured by the utilization of the static stability principle. Some typical experiments, including walking straight, turning, and avoiding obstacles, are performed for the developed quadruped salamander-like robot, with the collected results convincingly demonstrating the effectiveness of the proposed control method and the developed robot

Abstract:-The sense of touch is essential for reliable mapping between the environment and a robot which interacts physically with objects. Presumably, an artificial tactile skin would facilitate safe interaction of the robots with the environment. In this work, we present our color-coded tactile sensor, incorporating plastic optical fibers (POF), transparent silicone rubber and an off-the-shelf color camera. Processing electronics are placed away from the sensing surface to make the sensor robust to harsh environments. Contact localization is possible thanks to the lower number of light sources compared to the number of camera POFs. Classical machine learning techniques and a hierarchical classification scheme were used for contact localization.Specifically,wegeneratedthemappingfromstimulation to sensation of a robotic perception system using our sensor. We achieved a force sensing range up to 18 N with the force resolution of around 3.6 N and the spatial resolution of 8 mm. The color-coded tactile sensor is suitable for tactile exploration and might enable further innovations in robust tactile sensing

Abstract:-Optical coherence tomography (OCT) has found great success in ophthalmology where it plays a key role in screening and diagnostics. Clinical ophthalmic OCT systems are typically deployed as tabletop instruments that require chinrest stabilization and trained ophthalmic photographers to operate. These requirements preclude OCT diagnostics in bedbound or unconscious patients who cannot use a chinrest, and restrict OCT screening to ophthalmology offices. We present a robotically-aligned OCT scanner capable of automatic eye imaging without chinrests. The scanner features eye tracking from fixed-base RGB-D cameras for coarse and stereo pupil cameras for fine alignment, as well as galvanometer aiming for fast lateral tracking, reference arm adjustment for fast axial tracking, and a commercial robot arm for slow lateral and axial tracking. We demonstrate the system’s performance autonomously aligning with stationary eyes, pursuing moving eyes, and tracking eyes undergoing physiologic motion. The system demonstrates sub-millimeter eye tracking accuracy, 12µm lateral pupil tracking accuracy, 83.2ms stabilization time following step disturbance, and 9.7Hz tracking bandwidth. Index Terms—Medical robotics, optical coherence tomography, image stabilization

Abstract:-This paper evaluates the feasibility of a novel optical sensing concept to measure forces applied at the tip of davinci endowrist instruments. An optical slit is clapmped onto the instrument shaft, in-line with an infrared LED bicell pair deflection of the shaft moves the slit with respect to the led bicell pair modules the light incident on each active element of the bicell. The differential photocurrent is conditioned and monitored to estimate the tip forces. Keywords- Surgical Robotics: Laparoscopy, force and tactile sensing, haptics and haptic interfaces

Abstract:-Cloud Robotics is a paradigm where multiple robots are connected to cloud services via Internet to access “unlimited” computation power, at the cost of network communication. However, due to limitations such as network latency and variability, it is difficult to control dynamic, human compliant service robots directly from the cloud. In this work, we combine cloud robotics with an agile edge device to build a Fog Robotic system by leveraging an asynchronous protocol with a “heartbeat” signal. We use the system to enable robust teleoperation of a dynamic self-balancing robot from the cloud. We use the system to pick up boxes from static locations, a task commonly performed in warehouse logistics. To make cloud teleoperation more intuitive and efficient, we program a cloudbased image based visual servoing (IBVS) module to automatically assist the cloud teleoperator during the object pickups. Visual feedbacks, including apriltag recognition and tracking, are performed in the cloud to emulate a Fog Robotic object recognition system for IBVS. We demonstrate the feasibility of a dynamic real-time automation system using this cloudedge hybrid design, which opens up possibilities of deploying dynamic robotic control with deep-learning recognition systems in Fog Robotics. Finally, we show that Fog Robotics enables the self-balancing service robot to pick up a box automatically from a person under unstructured environments.

Abstract:-In this paper, we propose a novel navigation system for mobile robots in pedestrian-rich side walk environments. Sidewalks are unique in that the pedestrian-shared space has characteristics of both roads and indoor spaces. Like vehicles on roads, pedestrian movement often manifests as linear flows in opposing directions. On the other hand, pedestrians also form crowds and can exhibit much more random movements than vehicles. Classical algorithms are insufficient for safe navigation around pedestrians and remaining on the sidewalk space. Thus, our approach takes advantage of natural human motion to allow a robot to adapt to sidewalk navigation in a safe and socially-compliant manner. We developed a group surfing method which aims to imitate the optimal pedestrian group for bringing the robot closer to its goal. For pedestriansparse environments, we propose a sidewalk edge detection and following method. Underlying these two navigation methods, the collision avoidance scheme is human-aware. The integrated navigation stack is evaluated and demonstrated in simulation. A hardware demonstration is also presented

Abstract:-One of the significant challenges of moving from manual to robot-assisted retinal surgery is the loss of perception of forces applied to the sclera (sclera forces) by the surgical tools. This damping of force feedback is primarily due to the stiffness and inertia of the robot. The diminished perception of tool-to-eye interactions might put the eye tissue at high risk of injury due to excessive sclera forces or extreme insertion of the tool into the eye. In the present study therefore a 1-dimensional adaptivecontrolmethodiscustomizedfor3-dimensionalcontrol of sclera force components and tool insertion depth and then implemented on the velocity-controlled Johns Hopkins SteadyHand Eye Robot. The control method enables the robot to perform autonomous motions to make the sclera force and/or insertion depth of the tool tip to follow pre-defined desired and safe trajectories when they exceed safe bounds. A robotic light pipe holding application in retinal surgery is also investigated using the adaptive control method. The implementation results indicate that the adaptive control is able to achieve the imposed safety margins and prevent sclera forces and insertion depth from exceeding safe boundaries.

Abstract:-In this paper, a magnetic-field-inspired robot navigation is used to navigate an under-actuated quadcopter towards the desired position amidst previously-unknown arbitrary-shaped convex obstacles. Taking inspiration from the phenomena of magnetic field interaction with charged particles observedinnature,thealgorithmoutperformspreviousreactive navigation algorithms for flying robots found in the literature as it is able to reactively generate motion commands relying only on a local sensory information without prior knowledge of the obstacles’ shape or location and without getting trapped in local minima configurations. The application of the algorithm in a dynamic model of quadcopter system and in the realistic model of the commercial AscTec Pelican micro-aerial vehicle confirm the superior performance of the algorithm.

Abstract:-The growing demand of industrial, automotive and service robots presents a challenge to the centralized Cloud Robotics model in terms of privacy, security, latency, bandwidth, and reliability. In this paper, we present a ‘Fog Robotics’ approach to deep robot learning that distributes compute, storage and networking resources between the Cloud andtheEdgeinafederatedmanner.Deepmodelsaretrainedon non-private (public) synthetic images in the Cloud; the models are adapted to the private real images of the environment at the Edge within a trusted network and subsequently, deployed as a service for low-latency and secure inference/prediction for other robots in the network. We apply this approach to surface decluttering, where a mobile robot picks and sorts objects from a cluttered floor by learning a deep object recognition and a grasp planning model. Experiments suggest that Fog Robotics can improve performance by sim-to-real domain adaptation in comparison to exclusively using Cloud or Edge resources, while reducingtheinferencecycletimeby 4×tosuccessfullydeclutter 86% of objects over 213 attempts

Abstract:-Remoras employ their adhesive discs to rapidly attach to and detach from a wide range of marine surfaces. By analyzing high-speed images of remoras mechanism as a lip curling up to break the seal between the disc and substrate. By mimicking the kinematic and morphological properties of the biological disc, we fabricated a multi-material biomimetic disc (whose stiffness spans four orders of magnitude) that is capable of both attachment and detachment. Detachment is realized by a flexible cable-driven mechanism that curls the anterior region of the silicone soft lip, allows leakage under the disc, and equalizes the internal pressure to the external pressure. KeywordsAttachment and detachment, soft robotics, underwater adhesion.

Abstract:-Subretinal injection is known to be a complicated task for ophthalmologists to perform, the main sources of difficulties are the fine anatomy of the retina, insufficient visual feedback, and high surgical precision. Image guided robotassisted surgery is one of the promising solutions that bring significant surgical enhancement in treatment outcome and reduces the physical limitations of human surgeons. In this paper, we demonstrate a robust framework for needle detection and localization in subretinal injection using microscopeintegrated Optical Coherence Tomography (MI-OCT) based on deep learning. The proposed method consists of two main steps:a)thepreprocessingofOCTvolumetricimages;b)needle localization in the processed images. The first step is to coarsely localize the needle position based on the needle information above the retinal surface and crop the original image into a small region of interest (ROI). Afterward, the cropped small image is fed into a well trained network for detection and localization of the needle segment. The entire framework is extensivelyvalidatedinex-vivopigeyeexperimentswithrobotic subretinal injection. The results show that the proposed method can localize the needle accurately with a confidence of 99.2%.

Abstract:-This paper presents the design and testing of a bio-inspired soft pneumatic robot that can achieve locomotion along the outside of a cylinder. The robot uses soft pneumatic actuators called FREEs (Fiber Reinforced Elastomeric Enclosure), which can have a wide range of deformation behavior upon pressurization. The robot being soft and compliant can grasp and move along cylinders of varying dimensions. Two different types of FREEs are used in the robot namely (a) extending FREEs and (b) bending FREEs. These actuators are arranged in such a way that the bending actuators are used to grip the pipe while the extending actuators generate forward motion as well as bending for direction control. The modular design of the robot provides simplicity and ease of maintenance. The entire robot is made of flexible actuators and can withstand external impact with minimal to no damage. The maximum speed achieved for horizontal motion is 4.2 mm/s and for vertical motion is 2.1 mm/s.

Abstract:-Lower-limb exoskeleton has gained considerable interests in walking assistance applications for paraplegic patients. In walking assistance of paraplegic patients,theexoskeletonshouldhavetheabilitytohelppatientstowalkoverdifferent terrainsinthedailylife,suchasslopeterrains.Onecriticalissue is how to plan the stepping locations on slopes with different gradients,andgeneratestableandhuman-likegaitsforpatients. This paper proposed an adaptive gait planning approach which can generate gait trajectories adapt to slopes with different gradients for lower-limb walking assistance exoskeletons. We modeled the human-exoskeleton system as a 2DLinear Inverted Pendulum Model (2D-LIPM) with an external force in the two-dimensional sagittal plane, and proposed a Dynamic Gait Generator (DGG) based on an extension of the conventional Capture Point (CP) theory and Dynamic Movement Primitives (DMPs). The proposed approach can dynamically generate reference foot locations for each step on slopes, and human-like adaptive gait trajectories can be reproduced after the learning from demonstrated trajectories that sampled from level ground walking of normal healthy human. We demonstrated the efficiency of the proposed approach on both the Gazebo simulation platform and an exoskeleton named AIDER. Experimental results indicate that the proposed approach is able to provide the ability for exoskeletons to generate appropriate gaits adapt to slopes with different gradients. IndexTerms—AdaptiveGaitPlanning,Lower-limbExoskeleton, LIPM, Dynamic Movement Primitives, Slope

Abstract:-To match the ever increasing standards of fresh products, and the need to reduce waste, we devise an alternative to the destructive and highly variable fruit ripeness estimation by a penetrometer. We propose a fully automatic method to assess the ripeness of mango which is non-destructive, allows the user to test multiple surface areas with a single touch and is capable of dissociating between ripe and non-ripe fruits. A custom-made gripper equipped with a capacitive tactile sensor array is used to palpate the fruit. The ripeness is estimated as mango stiffness extracted through a simplified spring model. We test the framework on a set of 25 mangoes of the Keitt variety,andcomparetheresultstopenetrometermeasurements. We show it is possible to correctly classify 88% of the mango without removing the skin of the fruit. The method can be a valuable substitute for non-destructive fruit ripeness testing. To the authors knowledge, this is the first robotics ripeness estimation system based on capacitive tactile sensing technology

Abstract:-Most existing controllers for Car-Like Mobile Robots (CLMR) are designed to handle dynamic effects by decoupling speed and steering controls, also assume that full states are accessible, which are unrealistic for real-world applications. This paper presents a combined speed and steering control system for CLMR. To provide the essential state for the controller, a newly developed visual algorithm is adopted for estimating the high-update rate longitudinal and lateral velocities of the robot which cannot be accurately measured by wheel encoders due to the skidding and slipping effects. The stability of the proposed system can be guaranteed by Lyapunov method since the velocity estimation error, the speed tracking error and the lateral deviation converging to zero simultaneously. Real-world experiments are conducted on an electric autonomous tractor with online estimation to demonstrate the feasibility of the approach.

Abstract:-Underwater robots are subject to complex hydrodynamic forces. These forces define how the vehicle moves, so it is important to consider them when planning trajectories. However, performing motion planning considering the dynamics on the robot’s onboard computer is challenging due to the limited computational resources available. In this paper an efficient motion planning framework for autonomous underwater vehicles (AUVs) is presented. By introducing a loosely coupled multilayeredplanningdesign,ourframeworkisabletogenerate dynamically feasible trajectories while keeping the planning time low enough for online planning. First, a fast path planner operating in a lower-dimensional projected space computes a lead path from the start to the goal configuration. Then, the lead path is used to bias the sampling of a second motion planner, which takes into account all the dynamic constraints. Furthermore, we propose a strategy for online planning that savescomputationalresourcesby generatingthefinaltrajectory only up to a finite horizon. By using the finite horizon strategy together with the multilayered approach, the sampling of the second planner focuses on regions where good quality solutions are more likely to be found, significantly reducing the planning time. To provide strong safety guarantees our framework also incorporates the conservative approximations of inevitable collision states (ICSs). Finally, we present simulations and experiments using a real underwater robot to demonstrate the capabilities of our framework

Abstract:-Modern cities are growing ecosystems that face new challenges due to the increasing population demands. One ofthemanyproblemstheyfacenowadaysiswastemanagement, which has become a pressing issue requiring new solutions. Swarm robotics systems have been attracting an increasing amount of attention in the past years and they are expected to become one of the main driving factors for innovation in the field of robotics. The research presented in this paper explores the feasibility of a swarm robotics system in an urban environment. By using bio-inspired foraging methods such as multi-place foraging and stigmergy-based navigation, a swarm of robots is able to improve the efficiency and autonomy of the urban waste management system in a realistic scenario.Toachievethis,adiversesetofsimulationexperiments was conducted using real-world GIS data and implementing different garbage collection scenarios driven by robot swarms. Results presented in this research show that the proposed system outperforms current approaches. Moreover, results not only show the efficiency of our solution, but also give insights about how to design and customize these systems.

Abstract:-Accurate real-time estimation of the pose and configuration of the human hand attached to a dexterous haptic input device is crucial to improve the interaction possibilities for teleoperation and in virtual and augmented reality. In this paper, we present an approach to reconstruct the pose of the human hand and the joint angles of the fingers when wearing a novel fixed-base (grounded) hand exoskeleton. Using a kinematic model of the human hand built from MRI data, we can reconstruct the hand pose and joint angles without sensors on the human hand, from attachment points on the first three fingers and the palm. We test the accuracy of our approach using motion capture as a ground truth. This reconstruction can be used to determine contact geometry and force-feedback from virtual or remote objects in virtual reality or teleoperation

Abstract:-

Abstract:- A manipulation technique based on optothermally generated surface bubbles is proposed in this paper. The manipulation and assembly of microstructures are completed by using bubbles. In addition, the hydrogel microstructures are also used as microrobots driven by the bubble to operate and pattern the microspheres. Considering that many materials and lasers with different wavelength have been used for generating bubbles by optothermal effects, absorptivity and transmissivity are used as indicators of selections. Besides, the size of the bubble can be controlled by the frequency and time of the laser. This technique is supposed to be applied for manipulation of cells, microparticles and microstructures

Abstract:-We present a transformable catheter head structure for endoscopic catheter allowing the simultaneous use of a camera module and a large tool channel introduced through a small incision. At the site of interest, the head with a camera can be expanded from the initial straight configuration, which opens a window for advancing a tool that is located behind the camera. Two different designs were proposed and prototyped. Oneoptionhasflexurejointsdirectlyfabricatedatthedistalend of a polymer catheter by laser micro-machining, while another design employs a hinged metal head assembled at the tip of the same type of catheter. The kinematic behavior of each head was evaluated during the head-up and tip steering motions, and compared with each other to draw a selection guideline between them. Experimental results prove the feasibility of the proposed head structure for smarter endoscopic catheters.

Abstract:-The recent increase in the use of aerial vehicles raises concerns about the safety and reliability of autonomous operations. There is a growing need for methods to monitor the status of these aircraft and report any faults and anomalies to the safety pilot or to the autopilot to deal with the emergency situation. In this paper, we present a real-time approach using the Recursive Least Squares method to detect anomalies in the behavior of an aircraft. The method models the relationship betweencorrelatedinput-outputpairsonlineandusesthemodel to detect the anomalies. The result is an easy-to-deploy anomaly detection method that does not assume a specific aircraft model and can detect many types of faults and anomalies in a wide range of autonomous aircraft. The experiments on this method show a precision of 88.23%, recall of 88.23% and 86.36% accuracy for over 22 flight tests. The other contribution is providing a new fault detection open dataset for autonomous aircraft, which contains complete data and the ground truth for 22 fixed-wing flights with eight different types of mid-flight actuator failures to help future fault detection research for aircraft. The recent increase in the use of aerial vehicles raises concerns about the safety and reliability of autonomous operations. There is a growing need for methods to monitor the status of these aircraft and report any faults and anomalies to the safety pilot or to the autopilot to deal with the emergency situation. In this paper, we present a real-time approach using the Recursive Least Squares method to detect anomalies in the behavior of an aircraft. The method models the relationship betweencorrelatedinput-outputpairsonlineandusesthemodel to detect the anomalies. The result is an easy-to-deploy anomaly detection method that does not assume a specific aircraft model and can detect many types of faults and anomalies in a wide range of autonomous aircraft. The experiments on this method show a precision of 88.23%, recall of 88.23% and 86.36% accuracy for over 22 flight tests. The other contribution is providing a new fault detection open dataset for autonomous aircraft, which contains complete data and the ground truth for 22 fixed-wing flights with eight different types of mid-flight actuator failures to help future fault detection research for aircraft.

Abstract:-This paper presents the development of a fiber Bragg grating (FBG) bending sensor for shape memory alloy (SMA) bending modules. Due to the small form factor, low cost, and large-deflection capability, SMA bending modules can be used to construct disposable surgical robots for a variety of minimally invasive procedures. To realize a closedloop control of SMA bending modules, an intrinsic bending sensorisimperative.DuetothelackofbendingsensorsforSMA bending modules, we have developed an FBG bending sensor by integrating FBG fibers with a superelastic substrate using flexible adhesive. Since the substrate is ultra-thin and adhesive is flexible, the sensor has low stiffness and can measure large curvatures. Additionally, due to the orthogonal arrangement of the sensor/actuator assembly, the influence of temperature variation caused by SMA actuation can be compensated. The workingprincipleofthedevelopedsensorwasmodeledfollowed by simulations. After experimentally evaluating the developed model, the sensor was integrated with an SMA bending module and cyclically bi-directionally deflected. The experimental results proved the relatively high measurement accuracy, high repeatability, and large measurable curvatures of the sensor, although hysteresis was observed due to friction

Abstract:-In this paper, we present a whole-body control framework for Wheeled Inverted Pendulum (WIP) Humanoids. WIP Humanoids are redundant manipulators dynamically balancing themselves on wheels. Characterized by several degrees of freedom, they have the ability to perform several tasks simultaneously, such as balancing, maintaining a body pose, controlling the gaze, lifting a load or maintaining end-effector configuration in operation space. The problem of whole-body control is to enable simultaneous performance of these tasks with optimal participation of all degrees of freedom at specified priorities for each objective. The control also has to obey constraint of angle and torque limits on each joint. The proposed approach is hierarchical with a low level controller for body joints manipulation and a high-level controller that defines center of mass (CoM) targets for the low-level controller to control zero dynamics of the system driving the wheels. The low-level controller plans forshorter horizons while considering more complete dynamics of the system, while the high-level controller plans for longer horizon based on an approximate model of the robot for computational efficiency

Abstract:-In this paper, we present a method for depth control of one degree of freedom (1DOF) underwater robotic platform a Mussel, based on the measurements from the ambient light sensor. Since ambient light values change during the day and depend on the weather conditions, references for the controller are acquired from other aMussel holding depth using pressuresensorbasedcontroller.Control inputs are transmitted using acoustic communication.

Abstract:-Template matching has been shown to accurately estimate the pose of a new object given a limited number of samples. However, pose estimation of occluded objects is still challenging. Furthermore, many robot application domains encounter texture-less objects for which depth images are more suitable than color images. In this paper, we propose a novel framework,Multi-TaskTemplateMatching(MTTM),thatfinds the nearest template of a target object from a depth image while predicting segmentation masks and a pose transformation between the template and a detected object in the scene using the same feature map of the object region. The proposed feature comparison network computes segmentation masks and pose predictions by comparing feature maps of templates and cropped features of a scene. The segmentation result from this network improves the robustness of the pose estimation by excluding points that do not belong to the object. Experimental results show that MTTM outperforms baseline methods for segmentation and pose estimation of occluded objects despite using only depth images.

Abstract:-In this paper we describe the Open Vision Computer (OVC) which was designed to support high speed, vision guided autonomous drone flight. In particular our aim was to developasystemthatwouldbesuitableforrelativelysmall-scale flying platforms where size, weight, power consumption and computational performance were all important considerations. This manuscript describes the primary features of our OVC system and explains how they are used to support fully autonomous indoor and outdoor exploration and navigation operations on our Falcon 250 quadrotor platform

Abstract:-With recent advances in hardware technology, autonomous robots are increasingly present in research activities outside of robotics, performing a multitude of tasks such as image capture and sample collection. However, user interfaces for task-oriented robots have not kept pace with hardware breakthroughs. Current planning and control interfaces for robots are not intuitive and often place a large cognitive burden on those who are not highly trained in their use. Augmented reality (AR) has also seen major advances in recent years. This demonstration illustrates an initial system design for an AR user interface for path planning with robotics

Abstract:-The advancement of modern technology has become a significant role to assist human life these days to be more convenient, more accessible, more secure and more efficient. One of excellently new technology examples describes upcoming industrial technology is Industrial Internet of Thing (IIOT). This significant means to every machine device those are able to connect to the internet and exchange data to each other for the needs of consumer. The main purpose of this paper is desired to develop the concept of Smart Factory by enhancing efficiency of the active manufacturing that enable to interact with humans, and simply accessible by remote controlling. The system implementation is demonstrated by connecting wireless router to Programmable Logic Controller (PLC) which is the central controller supervising multiple machine devices in the system. This developing system, socalled “the Demo Site”, has the key feature to allow users to remote control all machine devices from anywhere and anytime by using Graphical User Interface via user’s smart devices. Therefore, the remote controlling system of the Demo Site has been developed to enhance the ability and efficiency of the system as to the concept of Smart Factory for Industry 4.0. Keywords—industry 4.0; remote controlling; smart factory; computer integrated manufacturing

Abstract:-AGV (Automated Guided Vehicle) has been widely used in industrial automation production. This paper presents an overall design scheme for laser guided AGV with reflector. Firstly, aiming at the laser positioning problem of AGV and the matching problem of laser reflector, a laser positioning algorithm based on coordinate system transformation and a reflector matching algorithm based on dead reckoning are proposed respectively. Secondly, the kinematic model modeling of differential drive AGV is completed for the trajectory tracking control problem. According to Lyapunov's direct method, the trajectory tracking control law is designed. The motion simulation of common trajectories is given on the MATLAB platform. Finally, the test prototype was designed and built. The test results at the industrial site show that the AGV can be accurately positioned in both static and dynamic states, and it can quickly converge to a predetermined trajectory after starting the operation. Keywords—AGV; positioning algorithm; matching algorithm; trajectory tracking

Abstract:-Unmanned aerial vehicles (UAVs) have increasingly been adopted for safety, security, and rescue missions, for which they need precise and reliable pose estimates relative to their environment. To ensure mission safety when relying on visual perception, it is essential to have an approach to assess the integrity of the visual localization solution. However, to the best of our knowledge, such an approach does not exist for optimization-based visual localization. Receiver autonomous integrity monitoring (RAIM) has been widely used in global navigation satellite systems (GNSS) applications such as automated aircraft landing. In this paper, we propose a novel approach inspired by RAIM to monitor the integrity of optimizationbased visual localization and calculate the protection level of a stateestimate,i.e.thelargestpossibletranslationalerrorineach direction.Wealsoproposeametricthatquantitativelyevaluates the performance of the error bounds. Finally, we validate the protection level using the EuRoC dataset and demonstrate that the proposed protection level provides a significantly more reliable bound than the commonly used 3σ method.