Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10121946
Chao Liu, Andrea Moncada, Hanna Matusik, Deniz Irem Erus, D. Rus
While parallel grippers and multi-fingered robotic hands are well developed and commonly used in structured settings, it remains a challenge in robotics to design a highly articulated robotic hand that can be comparable to human hands to handle various daily manipulation and grasping tasks. Dexterity usually requires more actuators but also leads to a more sophisticated mechanism design and is more expensive to fabricate and maintain. Soft materials are able to provide compliance and safety when interacting with the physical world but are hard to model. This work presents a hybrid bio-inspired robotic hand that combines soft matters and rigid elements. Sensing is integrated into the rigid bodies resulting in a simple way for pose estimation with high sensitivity. The proposed hand is in a modular structure allowing for rapid fabrication and programming. The fabrication process is carefully designed so that a full hand can be made with low-cost materials and assembled in an efficient manner. We demonstrate the dexterity of the hand by successfully performing human grasp types.
{"title":"A Modular Bio-inspired Robotic Hand with High Sensitivity","authors":"Chao Liu, Andrea Moncada, Hanna Matusik, Deniz Irem Erus, D. Rus","doi":"10.1109/RoboSoft55895.2023.10121946","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10121946","url":null,"abstract":"While parallel grippers and multi-fingered robotic hands are well developed and commonly used in structured settings, it remains a challenge in robotics to design a highly articulated robotic hand that can be comparable to human hands to handle various daily manipulation and grasping tasks. Dexterity usually requires more actuators but also leads to a more sophisticated mechanism design and is more expensive to fabricate and maintain. Soft materials are able to provide compliance and safety when interacting with the physical world but are hard to model. This work presents a hybrid bio-inspired robotic hand that combines soft matters and rigid elements. Sensing is integrated into the rigid bodies resulting in a simple way for pose estimation with high sensitivity. The proposed hand is in a modular structure allowing for rapid fabrication and programming. The fabrication process is carefully designed so that a full hand can be made with low-cost materials and assembled in an efficient manner. We demonstrate the dexterity of the hand by successfully performing human grasp types.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114089599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10122086
Metodi Netzev, Alexandre Angleraud, R. Pieters
Grasping parts of inconsistent shapes, sizes and weights securely requires accurate part models and custom gripper fingers. Compliant grippers are a potential solution; however, each design approach requires the solution of unique problems. In this case, the durability and reliability of half lips (at least 1400 cycles) to perform consistently as springs of a specified stiffness (0.5N/mm) and displacement (5mm). Moreover, the challenge of low and small (3mm, 0.01kg bolt or Allen key) objects is addressed through vertical squeeze-in, implemented using an incline, lip and flex limiter as part of a 3D printed TPC spring. The squeeze-in phenomena are verified on large objects through a 30mm, 1.66kg common rail. Experimental results demonstrate the reliability when given a human-specified location for gripping, without the need for jigs or fixtures. Finally, the tested design is assessed for potential fulfillment of 7 of the United Nations sustainable development goals.
{"title":"Squeeze-in Functionality for a Soft Parallel Robot Gripper","authors":"Metodi Netzev, Alexandre Angleraud, R. Pieters","doi":"10.1109/RoboSoft55895.2023.10122086","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10122086","url":null,"abstract":"Grasping parts of inconsistent shapes, sizes and weights securely requires accurate part models and custom gripper fingers. Compliant grippers are a potential solution; however, each design approach requires the solution of unique problems. In this case, the durability and reliability of half lips (at least 1400 cycles) to perform consistently as springs of a specified stiffness (0.5N/mm) and displacement (5mm). Moreover, the challenge of low and small (3mm, 0.01kg bolt or Allen key) objects is addressed through vertical squeeze-in, implemented using an incline, lip and flex limiter as part of a 3D printed TPC spring. The squeeze-in phenomena are verified on large objects through a 30mm, 1.66kg common rail. Experimental results demonstrate the reliability when given a human-specified location for gripping, without the need for jigs or fixtures. Finally, the tested design is assessed for potential fulfillment of 7 of the United Nations sustainable development goals.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122386695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10122056
Xinquan Liang, Yuzhe Wang, Xie Zhen, S. Ocak
Performing adaptive grasping tasks with unknown shapes is challenging for robotic grippers. The emergence of soft robotics brings a new perspective to address this challenge, since soft robots have unique merits of lightweight, inherent softness and natural compliance owing to the soft materials and actuation methods. In this paper, inspired by soft mesh structures, we propose a soft robotic gripper based on flexible 3D-printed mesh skeleton. With this new design, the soft gripper can effectively contract and grasp various objects upon vacuum actuation. The 3D-printed stretchable mesh allows the gripper to perfectly match the shapes of target objects in less than 1s. This compliant feature allows the soft gripper to safely handle fragile objects, with the potential to be customized for specific objects and tasks. The developed gripper is expected to be useful for various pick-and-place tasks such as food handling, cosmetic packaging, and fruit picking.
{"title":"A Vacuum-Powered Soft Mesh Gripper for Compliant and Effective Grasping","authors":"Xinquan Liang, Yuzhe Wang, Xie Zhen, S. Ocak","doi":"10.1109/RoboSoft55895.2023.10122056","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10122056","url":null,"abstract":"Performing adaptive grasping tasks with unknown shapes is challenging for robotic grippers. The emergence of soft robotics brings a new perspective to address this challenge, since soft robots have unique merits of lightweight, inherent softness and natural compliance owing to the soft materials and actuation methods. In this paper, inspired by soft mesh structures, we propose a soft robotic gripper based on flexible 3D-printed mesh skeleton. With this new design, the soft gripper can effectively contract and grasp various objects upon vacuum actuation. The 3D-printed stretchable mesh allows the gripper to perfectly match the shapes of target objects in less than 1s. This compliant feature allows the soft gripper to safely handle fragile objects, with the potential to be customized for specific objects and tasks. The developed gripper is expected to be useful for various pick-and-place tasks such as food handling, cosmetic packaging, and fruit picking.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121378278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10122016
Haley Sanders, Marc D. Killpack
Potential applications for large-scale soft robots include interacting with humans while carrying a heavy load, navigating in clutter, executing impact tasks like hammering a nail into a wall, and so much more. Because of their compliance and lack of fragile gear trains, soft robots are uniquely suited to these tasks. However, we expect that path planning may be more constrained by soft robot kinematics and dynamics than traditional rigid robots. Generating dynamically feasible trajectories for soft robots (especially large-scale soft robots with higher payloads) is critical to the success of low-level controllers tracking reference trajectories. This paper introduces an optimization method to generate task and joint space trajectories for soft robots that satisfy kinematic and dynamic constraints which are unique to large-scale soft robots. The method presented in this paper is an offline trajectory generator that is then fed to a low-level PID joint angle controller. We conduct two experiments to validate this method on a continuum pneumatic soft robot of length 1.19 meters in both simulation and on hardware. We show that this is a viable method of planning trajectories for soft robots with a reported median magnitude of error of 0.032 meters between the planned and actual end effector trajectories.
{"title":"Dynamically Feasible Trajectory Generation for Soft Robots","authors":"Haley Sanders, Marc D. Killpack","doi":"10.1109/RoboSoft55895.2023.10122016","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10122016","url":null,"abstract":"Potential applications for large-scale soft robots include interacting with humans while carrying a heavy load, navigating in clutter, executing impact tasks like hammering a nail into a wall, and so much more. Because of their compliance and lack of fragile gear trains, soft robots are uniquely suited to these tasks. However, we expect that path planning may be more constrained by soft robot kinematics and dynamics than traditional rigid robots. Generating dynamically feasible trajectories for soft robots (especially large-scale soft robots with higher payloads) is critical to the success of low-level controllers tracking reference trajectories. This paper introduces an optimization method to generate task and joint space trajectories for soft robots that satisfy kinematic and dynamic constraints which are unique to large-scale soft robots. The method presented in this paper is an offline trajectory generator that is then fed to a low-level PID joint angle controller. We conduct two experiments to validate this method on a continuum pneumatic soft robot of length 1.19 meters in both simulation and on hardware. We show that this is a viable method of planning trajectories for soft robots with a reported median magnitude of error of 0.032 meters between the planned and actual end effector trajectories.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125809649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10122106
Mary C. Doerfler, Katalin Schäffer, Margaret M. Coad
Spider monkeys (genus Ateles) have a prehensile tail that functions as a flexible, multipurpose fifth limb, enabling them to navigate complex terrains, grasp objects of various sizes, and swing between supports. Inspired by the spider monkey tail, we present a life size hybrid soft-rigid continuum robot designed to imitate the function of the tail. Our planar design has a rigid skeleton with soft elements at its joints that achieve decreasing stiffness along its length. Five manually-operated wires along this central structure control the motion of the tail to form a variety of possible shapes in the 2D plane. Our design also includes a skin-like silicone and fabric tail pad that moves with the tail's tip and assists with object grasping. We quantify the force required to pull various objects out of the robot's grasp and demonstrate that this force increases with the object diameter and the number of edges in a polygonal object. We demonstrate the robot's ability to grasp, move, and release objects of various diameters, as well as to navigate around obstacles, and to retrieve an object after passing under a low passageway.
{"title":"Hybrid Soft-Rigid Continuum Robot Inspired by Spider Monkey Tail","authors":"Mary C. Doerfler, Katalin Schäffer, Margaret M. Coad","doi":"10.1109/RoboSoft55895.2023.10122106","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10122106","url":null,"abstract":"Spider monkeys (genus Ateles) have a prehensile tail that functions as a flexible, multipurpose fifth limb, enabling them to navigate complex terrains, grasp objects of various sizes, and swing between supports. Inspired by the spider monkey tail, we present a life size hybrid soft-rigid continuum robot designed to imitate the function of the tail. Our planar design has a rigid skeleton with soft elements at its joints that achieve decreasing stiffness along its length. Five manually-operated wires along this central structure control the motion of the tail to form a variety of possible shapes in the 2D plane. Our design also includes a skin-like silicone and fabric tail pad that moves with the tail's tip and assists with object grasping. We quantify the force required to pull various objects out of the robot's grasp and demonstrate that this force increases with the object diameter and the number of edges in a polygonal object. We demonstrate the robot's ability to grasp, move, and release objects of various diameters, as well as to navigate around obstacles, and to retrieve an object after passing under a low passageway.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115948345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10122041
Jialei Shi, Wenlong Gaozhang, Hanyu Jin, Ge Shi, H. Wurdemann
Driven by performance criteria and requirements from specific applications in healthcare for instance, the soft robotics community has created a huge amount of different designs for pneumatically actuated soft robots. The assessment with regard to these criteria usually involves a full characterisation of the soft robotic system. In order to support these efforts during the prototyping phase and standardise assessment procedures, a physical platform is described in this paper that allows to gain essential insights into the characterisation and validation of control algorithms for pneumatically driven soft robots. The platform can be connected to a MATLAB Graphical User Interface allowing to send pressure values as well as record and plot data, and, hence, it is able to actuate and characterise main features of soft robots, such as the kinematics/dynamics, stiffness and force capability. The user can choose between two control units including the NI USB-6341 and Arduino Due. These components facilitate implementing and validating control algorithms using different tools, e.g., MATLAB/Simulink. To demonstrate the feasibility and functionalities of our platform, three soft robotic systems have been analysed. We present characterisation results for a variable stiffness joint, the kinematics results during the inflation of an elastic membrane and the validation of an open-loop control strategy for a soft continuum robot.
{"title":"Characterisation and control platform for pneumatically driven soft robots: Design and applications","authors":"Jialei Shi, Wenlong Gaozhang, Hanyu Jin, Ge Shi, H. Wurdemann","doi":"10.1109/RoboSoft55895.2023.10122041","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10122041","url":null,"abstract":"Driven by performance criteria and requirements from specific applications in healthcare for instance, the soft robotics community has created a huge amount of different designs for pneumatically actuated soft robots. The assessment with regard to these criteria usually involves a full characterisation of the soft robotic system. In order to support these efforts during the prototyping phase and standardise assessment procedures, a physical platform is described in this paper that allows to gain essential insights into the characterisation and validation of control algorithms for pneumatically driven soft robots. The platform can be connected to a MATLAB Graphical User Interface allowing to send pressure values as well as record and plot data, and, hence, it is able to actuate and characterise main features of soft robots, such as the kinematics/dynamics, stiffness and force capability. The user can choose between two control units including the NI USB-6341 and Arduino Due. These components facilitate implementing and validating control algorithms using different tools, e.g., MATLAB/Simulink. To demonstrate the feasibility and functionalities of our platform, three soft robotic systems have been analysed. We present characterisation results for a variable stiffness joint, the kinematics results during the inflation of an elastic membrane and the validation of an open-loop control strategy for a soft continuum robot.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114666500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10122050
Oki Morikage, Zhongkui Wang, S. Hirai, Akira Nonaka
In Japan, there is a growing demand for auto-mated silkworm farming system. In this paper, we propose a soft robotic gripper which can grasp silkworm and perform splitting operation after mating. The gripper consists of two soft fingers driven by the pulling motion of an air cylinder for the silkworm grasping. A soft belt driven by the same cylinder performs the splitting operation by a rotation motion. Samples of male and female silkworms were fabricated using silicone rubber were used in the splitting experiments. Two types of soft belts with flat and pleated geometries were experimental tested and the success rate was found to be higher with the pleated typed belt. Appropriate operation conditions were also found through the splitting experiments using the silkworm samples. Finally, experiments were performed on living silkworms provided by our industrial partner and the split operation was successful.
{"title":"A Soft Gripper for Automating Split Operation of Silkworm","authors":"Oki Morikage, Zhongkui Wang, S. Hirai, Akira Nonaka","doi":"10.1109/RoboSoft55895.2023.10122050","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10122050","url":null,"abstract":"In Japan, there is a growing demand for auto-mated silkworm farming system. In this paper, we propose a soft robotic gripper which can grasp silkworm and perform splitting operation after mating. The gripper consists of two soft fingers driven by the pulling motion of an air cylinder for the silkworm grasping. A soft belt driven by the same cylinder performs the splitting operation by a rotation motion. Samples of male and female silkworms were fabricated using silicone rubber were used in the splitting experiments. Two types of soft belts with flat and pleated geometries were experimental tested and the success rate was found to be higher with the pleated typed belt. Appropriate operation conditions were also found through the splitting experiments using the silkworm samples. Finally, experiments were performed on living silkworms provided by our industrial partner and the split operation was successful.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128580525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10122079
Jonathan William Ambrose, Dylan Sin You Cheah, R. C. Yeow
Soft robotic actuators possess several unique characteristics, such as being generally compliant and lightweight, making them suitable for safe human interaction to be deployed in various industries. However, they are often designed for an intended purpose, making them impractical for a different task. This paper aims to introduce a new way of utilising a new class of soft silicone actuators capable of incorporating them into applications that require both pushing and pulling. The dual multilayer extension actuator (DMEA) is compact and lightweight at 8 g, capable of an extension ratio of 300% and a high pulling force-to-weight ratio of 200 with the assistance of vacuum pressure at 30% extension ratio. The fabrication of the DMEA is described in detail and followed by characterisation tests of the DMEA compared to the FEA model. Finally, we showcase the DMEA pulling a 3D-printed arm as a potential assistive device and demonstrate the DMEA versatility by deploying the DMEA onto everyday household products like scissors and kitchen tongs.
{"title":"Dual Multilayer Extension Actuator for High Extension and High Compression Force Applications","authors":"Jonathan William Ambrose, Dylan Sin You Cheah, R. C. Yeow","doi":"10.1109/RoboSoft55895.2023.10122079","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10122079","url":null,"abstract":"Soft robotic actuators possess several unique characteristics, such as being generally compliant and lightweight, making them suitable for safe human interaction to be deployed in various industries. However, they are often designed for an intended purpose, making them impractical for a different task. This paper aims to introduce a new way of utilising a new class of soft silicone actuators capable of incorporating them into applications that require both pushing and pulling. The dual multilayer extension actuator (DMEA) is compact and lightweight at 8 g, capable of an extension ratio of 300% and a high pulling force-to-weight ratio of 200 with the assistance of vacuum pressure at 30% extension ratio. The fabrication of the DMEA is described in detail and followed by characterisation tests of the DMEA compared to the FEA model. Finally, we showcase the DMEA pulling a 3D-printed arm as a potential assistive device and demonstrate the DMEA versatility by deploying the DMEA onto everyday household products like scissors and kitchen tongs.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"281 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125864002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10121997
Tristan Sim Yook Min, Loong Yi Lee, S. Nurzaman
Design optimization of soft grippers is critical to functionally exploit their compliance. However, it is difficult to predictably model or search the design space of even simple Fluidic Elastomer Actuators. This work presents a method to rapidly customize and identify desirable morphologies of pneumatic soft grippers via Bayesian Optimization of reconfigurable modular molds. With the goal of maximizing grasping success rate for a general object set, the reality-assisted optimization process uses results from physical pick and place experiments to iterate through a large array of design parameters. Suggested design parameters dictate the assembly of pre-fabricated modules in the mold to generate silicone-casted soft fingers. These fingers are integrated to form a gripper and tested to inform the next iteration. This process allows faster iterations compared to 3D printing equivalent grippers or molds, and discretizes the design space for faster search through parameter combinations. An improvement of 34% in average grasping success rate was achieved in six iterations, shedding light on desirable parameter configurations for the grasping task.
{"title":"Bayesian Optimization of Pneumatic Soft Grippers via Reconfigurable Modular Molds","authors":"Tristan Sim Yook Min, Loong Yi Lee, S. Nurzaman","doi":"10.1109/RoboSoft55895.2023.10121997","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10121997","url":null,"abstract":"Design optimization of soft grippers is critical to functionally exploit their compliance. However, it is difficult to predictably model or search the design space of even simple Fluidic Elastomer Actuators. This work presents a method to rapidly customize and identify desirable morphologies of pneumatic soft grippers via Bayesian Optimization of reconfigurable modular molds. With the goal of maximizing grasping success rate for a general object set, the reality-assisted optimization process uses results from physical pick and place experiments to iterate through a large array of design parameters. Suggested design parameters dictate the assembly of pre-fabricated modules in the mold to generate silicone-casted soft fingers. These fingers are integrated to form a gripper and tested to inform the next iteration. This process allows faster iterations compared to 3D printing equivalent grippers or molds, and discretizes the design space for faster search through parameter combinations. An improvement of 34% in average grasping success rate was achieved in six iterations, shedding light on desirable parameter configurations for the grasping task.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124218818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1109/RoboSoft55895.2023.10121933
S. Nagasawa, V. A. Ho
Soft haptic sensing interfaces based on optical methods using cameras are characterized by their simplicity in design with less complication in terms of wiring, maintenance, and so on. Also, thanks to the fact that the mechanical properties of the flexible outer skin used in such vision-based tactile sensor are not compromised, promising in high reliability with respect to noise. On the other hand, when the sensing area increases, two or more cameras need to be setup behind the soft skin for monitoring markers' displacements. Previously, we developed a barrel-shaped tactile sensor with two cameras setup at two ends of the device for extraction of three-dimensional (3-D) movement of markers. However, simultaneously processing multiple images from cameras requires much computational effort. In this paper, we describe a 3-D estimation method using the rotation of a fisheye camera setup inside the soft skin's boundary, active by a simple servo motor. Based on rotation of the camera, the sensing time, sensitivity can be adjusted actively. The proposed method not only improves the usable volume inside the sensor, but also shows more robust measurement performance with respect to deformation of the sensor's outer skin.
{"title":"Three-Dimensional Shape Construction in a Soft Large-Scale Vision-based Tactile Sensor with a Single Rotational Camera","authors":"S. Nagasawa, V. A. Ho","doi":"10.1109/RoboSoft55895.2023.10121933","DOIUrl":"https://doi.org/10.1109/RoboSoft55895.2023.10121933","url":null,"abstract":"Soft haptic sensing interfaces based on optical methods using cameras are characterized by their simplicity in design with less complication in terms of wiring, maintenance, and so on. Also, thanks to the fact that the mechanical properties of the flexible outer skin used in such vision-based tactile sensor are not compromised, promising in high reliability with respect to noise. On the other hand, when the sensing area increases, two or more cameras need to be setup behind the soft skin for monitoring markers' displacements. Previously, we developed a barrel-shaped tactile sensor with two cameras setup at two ends of the device for extraction of three-dimensional (3-D) movement of markers. However, simultaneously processing multiple images from cameras requires much computational effort. In this paper, we describe a 3-D estimation method using the rotation of a fisheye camera setup inside the soft skin's boundary, active by a simple servo motor. Based on rotation of the camera, the sensing time, sensitivity can be adjusted actively. The proposed method not only improves the usable volume inside the sensor, but also shows more robust measurement performance with respect to deformation of the sensor's outer skin.","PeriodicalId":250981,"journal":{"name":"2023 IEEE International Conference on Soft Robotics (RoboSoft)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133929075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：