Pub Date : 2022-05-23DOI: 10.1109/icra46639.2022.9811864
E. Yousefi, Dylan P. Losey, I. Sharf
Operating an articulated machine is a complex and hierarchical task, involving several levels of decision making. Motivated by the timber-harvesting applications of these machines, we are interested in developing a collaborative framework for operating an articulated machine/robot in order to increase its level of autonomy. In this paper, we consider two problems in the context of collaborative operation of a feller-buncher: first, the problem of planning a sequence of cut/grasp/bunch tasks for the trees in the vicinity of the machine. Here we propose a human-inspired planning algorithm based on our observations of the operators in the field. Then, a Markov Decision Process (MDP) framework is provided, which enables us to obtain an optimal sequence of tasks. We provide numerical illustrations of how our MDP framework works. Second is the problem of inferring the operator's goal from the motions of the machine. The goal inference algorithm presented here enables the robot equipped with the planning intelligence to perceive the human's intent in real-time. We evaluate the performance of our goal inference algorithm through a user-study with a feller-buncher simulator. The results show the benefits of our algorithm over a robot that assumes the human is moving to the closest target.
{"title":"Assisting Operators of Articulated Machinery with Optimal Planning and Goal Inference","authors":"E. Yousefi, Dylan P. Losey, I. Sharf","doi":"10.1109/icra46639.2022.9811864","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811864","url":null,"abstract":"Operating an articulated machine is a complex and hierarchical task, involving several levels of decision making. Motivated by the timber-harvesting applications of these machines, we are interested in developing a collaborative framework for operating an articulated machine/robot in order to increase its level of autonomy. In this paper, we consider two problems in the context of collaborative operation of a feller-buncher: first, the problem of planning a sequence of cut/grasp/bunch tasks for the trees in the vicinity of the machine. Here we propose a human-inspired planning algorithm based on our observations of the operators in the field. Then, a Markov Decision Process (MDP) framework is provided, which enables us to obtain an optimal sequence of tasks. We provide numerical illustrations of how our MDP framework works. Second is the problem of inferring the operator's goal from the motions of the machine. The goal inference algorithm presented here enables the robot equipped with the planning intelligence to perceive the human's intent in real-time. We evaluate the performance of our goal inference algorithm through a user-study with a feller-buncher simulator. The results show the benefits of our algorithm over a robot that assumes the human is moving to the closest target.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122338986","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 : 2022-05-23DOI: 10.1109/icra46639.2022.9811366
P. Richard, François Morin, M. Lepage, P. Hamelin, G. Lambert, A. Sartor, Camille Hébert, N. Pouliot
Even if UAVs undoubtedly had a profound effect on the visual inspection capabilities of transmission lines, rolling robots, especially for bundled configurations, will still play an extensive role in the maintenance of these strategic assets. As such, LineRanger is among the most efficient and capable wheeled platform, that can travel at an average speed of 8 km/h. In this paper, LineRanger mechanical design insights are shared, unfolding how strictly mechanical solutions deals with ease of obstacle crossing, ease of installation procedure without requiring any linemen to access the high voltage environment area, and ease of deployment of dedicated, custom-made sensors onto the line component of interest. This novel robotic platform is now being deployed onto Hydro-Quebec power grid network, performing high value applications.
{"title":"Inside LineRanger: Mechanism Design to Optimize Operation and Performances of Powerline Inspection Robot","authors":"P. Richard, François Morin, M. Lepage, P. Hamelin, G. Lambert, A. Sartor, Camille Hébert, N. Pouliot","doi":"10.1109/icra46639.2022.9811366","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811366","url":null,"abstract":"Even if UAVs undoubtedly had a profound effect on the visual inspection capabilities of transmission lines, rolling robots, especially for bundled configurations, will still play an extensive role in the maintenance of these strategic assets. As such, LineRanger is among the most efficient and capable wheeled platform, that can travel at an average speed of 8 km/h. In this paper, LineRanger mechanical design insights are shared, unfolding how strictly mechanical solutions deals with ease of obstacle crossing, ease of installation procedure without requiring any linemen to access the high voltage environment area, and ease of deployment of dedicated, custom-made sensors onto the line component of interest. This novel robotic platform is now being deployed onto Hydro-Quebec power grid network, performing high value applications.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122681605","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 : 2022-05-23DOI: 10.1109/icra46639.2022.9811751
Fatemeh Zahra Saberifar, Dylan A. Shell, J. O’Kane
Practical robot designs must strike a compromise between fabrication/manufacture cost and anticipated execution performance. Compared to parsimonious designs, more capable (and hence more expensive) robots generally achieve their ends with greater efficiency. This paper examines how the roboticist might explore the space of designs to gain an understanding of such trade-offs. We focus, specifically, on design choices that alter the set of actions available to the robot, and model those actions as involving uncertainty. We consider planning problems under the Markov Decision Process (MDP) model, which leads us to examine how to relate the cost of some design to the expected cost of an execution for the optimal policies feasible with that design. The complexity of this problem ─expressed via hardness in the fixed parameter tractability sense─depends on the number of actions to choose from. When that number is not negligible, we give a novel representation and an algorithm utilizing that structure that allows useful savings over naïve enumeration.
{"title":"Charting the trade-off between design complexity and plan execution under probabilistic actions","authors":"Fatemeh Zahra Saberifar, Dylan A. Shell, J. O’Kane","doi":"10.1109/icra46639.2022.9811751","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811751","url":null,"abstract":"Practical robot designs must strike a compromise between fabrication/manufacture cost and anticipated execution performance. Compared to parsimonious designs, more capable (and hence more expensive) robots generally achieve their ends with greater efficiency. This paper examines how the roboticist might explore the space of designs to gain an understanding of such trade-offs. We focus, specifically, on design choices that alter the set of actions available to the robot, and model those actions as involving uncertainty. We consider planning problems under the Markov Decision Process (MDP) model, which leads us to examine how to relate the cost of some design to the expected cost of an execution for the optimal policies feasible with that design. The complexity of this problem ─expressed via hardness in the fixed parameter tractability sense─depends on the number of actions to choose from. When that number is not negligible, we give a novel representation and an algorithm utilizing that structure that allows useful savings over naïve enumeration.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122990412","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 : 2022-05-23DOI: 10.1109/icra46639.2022.9812021
Dengpeng Xing, Wannian Xia, Bo Xu
Kinematics and instantaneous kinematics are fundamental in many robotic tasks, such as positioning and collision avoidance. Existing learning methods mainly concern a single robot, and small-scale networks are sufficient for considerable approximation accuracy. A question is: Can we learn a kinematics model that can generalize to various robots rather than a single robot? This paper studies the kinematics learning of massive heterogeneous serial robots and the transfer of these general models to reality. We generate a dataset by randomizing dimensions, configurations, and link lengths and employ a network based on the generative pre-trained transformer to learn general kinematics mappings. We directly transfer our models for accuracy and use distillation-based transfer for computational efficiency. The results validate that our method can accurately approximate the kinematics of thousands of robot models and demonstrates generality in transfer.
{"title":"Kinematics Learning of Massive Heterogeneous Serial Robots","authors":"Dengpeng Xing, Wannian Xia, Bo Xu","doi":"10.1109/icra46639.2022.9812021","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9812021","url":null,"abstract":"Kinematics and instantaneous kinematics are fundamental in many robotic tasks, such as positioning and collision avoidance. Existing learning methods mainly concern a single robot, and small-scale networks are sufficient for considerable approximation accuracy. A question is: Can we learn a kinematics model that can generalize to various robots rather than a single robot? This paper studies the kinematics learning of massive heterogeneous serial robots and the transfer of these general models to reality. We generate a dataset by randomizing dimensions, configurations, and link lengths and employ a network based on the generative pre-trained transformer to learn general kinematics mappings. We directly transfer our models for accuracy and use distillation-based transfer for computational efficiency. The results validate that our method can accurately approximate the kinematics of thousands of robot models and demonstrates generality in transfer.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114577390","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 : 2022-05-23DOI: 10.1109/icra46639.2022.9811754
D. Fernández‐Gutiérrez, Niklas Hagemann, Wei Wang, Rens M. Doornbusch, Joshua Jordan, Jonathan Schiphorst, Pietro Leoni, Fábio Duarte, C. Ratti, D. Rus
Autonomous latching is essential for autonomous surface vessels (ASV) to reach full independence from human intervention. As part of the ASV Roboat project, a new solution for self-latching maneuvers has been developed and is presented here. We propose a system that has the key requirements of full integration with the navigation control system and zero-gap connection with the dock, the latter being essential for wireless charging of the ASV. Dedicated markers are used to identify docking targets, relying on computer vision algorithms to determine distance and bearing to the target. In its idle state, the locking solution uses mechanical power-off brakes, minimizing energy consumption while ensuring the boat stays in position indefinitely once docked. A prototype of the proposed mechanism has been built and installed in Roboat. Experimental tests showing the mechanism performance and capability to autonomously approach the docking station are discussed in this work.
{"title":"Design of an Autonomous Latching System for Surface Vessels","authors":"D. Fernández‐Gutiérrez, Niklas Hagemann, Wei Wang, Rens M. Doornbusch, Joshua Jordan, Jonathan Schiphorst, Pietro Leoni, Fábio Duarte, C. Ratti, D. Rus","doi":"10.1109/icra46639.2022.9811754","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811754","url":null,"abstract":"Autonomous latching is essential for autonomous surface vessels (ASV) to reach full independence from human intervention. As part of the ASV Roboat project, a new solution for self-latching maneuvers has been developed and is presented here. We propose a system that has the key requirements of full integration with the navigation control system and zero-gap connection with the dock, the latter being essential for wireless charging of the ASV. Dedicated markers are used to identify docking targets, relying on computer vision algorithms to determine distance and bearing to the target. In its idle state, the locking solution uses mechanical power-off brakes, minimizing energy consumption while ensuring the boat stays in position indefinitely once docked. A prototype of the proposed mechanism has been built and installed in Roboat. Experimental tests showing the mechanism performance and capability to autonomously approach the docking station are discussed in this work.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121979796","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 : 2022-05-23DOI: 10.1109/icra46639.2022.9811853
P. Franceschi, N. Pedrocchi, M. Beschi
The problem addressed in this work is the arbitration of the role between a robot and a human during physical Human-Robot Interaction, sharing a common task. The system is modeled as a Cartesian impedance, with two separate external forces provided by the human and the robot. The problem is then reformulated as a Cooperative Differential Game, which possibly has multiple solutions on the Pareto frontier. Finally, the bargaining problem is addressed by proposing a solution depending on the interaction force, interpreted as the human will to lead or follow. This defines the arbitration law and assigns the role of leader or follower to the robot. Experiments show the feasibility and capabilities of the proposed control in managing the human-robot arbitration during a shared- trajectory following task.
{"title":"Adaptive Impedance Controller for Human-Robot Arbitration based on Cooperative Differential Game Theory","authors":"P. Franceschi, N. Pedrocchi, M. Beschi","doi":"10.1109/icra46639.2022.9811853","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811853","url":null,"abstract":"The problem addressed in this work is the arbitration of the role between a robot and a human during physical Human-Robot Interaction, sharing a common task. The system is modeled as a Cartesian impedance, with two separate external forces provided by the human and the robot. The problem is then reformulated as a Cooperative Differential Game, which possibly has multiple solutions on the Pareto frontier. Finally, the bargaining problem is addressed by proposing a solution depending on the interaction force, interpreted as the human will to lead or follow. This defines the arbitration law and assigns the role of leader or follower to the robot. Experiments show the feasibility and capabilities of the proposed control in managing the human-robot arbitration during a shared- trajectory following task.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122121080","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}
Collision-free navigation while moving amongst static and dynamic obstacles with a limited sensor range is still a great challenge for modern mobile robots. Therefore, the ability to avoid collisions with obstacles in crowded, partially observable environments is one of the most important indicators to measure the navigation performance of a mobile robot. In this paper, we propose a novel deep reinforcement learning architecture that combines a spatial graph and attention rea-soning to tackle this problem. We take the relative positions and velocities of observed humans as nodes of the spatial graph and robot-human pairs as nodes of the attention graph to capture the spatial relations between the robot and the humans. In this way, our approach enhances the modeling of the relationship between the moving robot, static obstacles, and the people in the surrounding. As a result, our proposed navigation framework significantly outperforms state-of-the-art approaches [1], [2] in crowded scenarios when the robot has only a limited sensor range in terms of a reduced collision rate. Furthermore, we realize a seriously decreased training time by applying parallel Double Deep Q-Learning.
{"title":"Enhanced Spatial Attention Graph for Motion Planning in Crowded, Partially Observable Environments","authors":"Weixian Shi, Yanying Zhou, Xiangyu Zeng, Shijie Li, Maren Bennewitz","doi":"10.1109/icra46639.2022.9812322","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9812322","url":null,"abstract":"Collision-free navigation while moving amongst static and dynamic obstacles with a limited sensor range is still a great challenge for modern mobile robots. Therefore, the ability to avoid collisions with obstacles in crowded, partially observable environments is one of the most important indicators to measure the navigation performance of a mobile robot. In this paper, we propose a novel deep reinforcement learning architecture that combines a spatial graph and attention rea-soning to tackle this problem. We take the relative positions and velocities of observed humans as nodes of the spatial graph and robot-human pairs as nodes of the attention graph to capture the spatial relations between the robot and the humans. In this way, our approach enhances the modeling of the relationship between the moving robot, static obstacles, and the people in the surrounding. As a result, our proposed navigation framework significantly outperforms state-of-the-art approaches [1], [2] in crowded scenarios when the robot has only a limited sensor range in terms of a reduced collision rate. Furthermore, we realize a seriously decreased training time by applying parallel Double Deep Q-Learning.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122201161","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 : 2022-05-23DOI: 10.1109/icra46639.2022.9811867
S. Dorn, Nicola Wolpert, E. Schomer
We present the first realization of an assembly sequence planning framework for large-scale and complex 3D real-world CAD scenarios. Other than in academic benchmark data sets, in our scenario each assembled part is allowed to contain flexible fastening elements and the number of assembled parts is quite high. With our framework we are able to derive a meaningful assembly priority graph for the parts. Our framework divides the disassembly motion of each part into a NEAR- and a subsequent FAR planning phase and uses existing specialized motion planners for each phase. To reduce the number of unsuccessful motion planning requests we use a general Voronoi diagram graph and a novel collision perceiving method which significantly speed up our framework. At the end, we create an assembly priority graph to indicate which parts must be disassembled before others. In our experiments, we show that our framework is the first one which is able to generate a priority graph for a representative data set from the automotive industry. Moreover, the reported disassembly motions for the individual parts are shorter and can be computed faster than with other state-of-the-art frameworks.
{"title":"An Assembly Sequence Planning Framework for Complex Data using General Voronoi Diagram","authors":"S. Dorn, Nicola Wolpert, E. Schomer","doi":"10.1109/icra46639.2022.9811867","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9811867","url":null,"abstract":"We present the first realization of an assembly sequence planning framework for large-scale and complex 3D real-world CAD scenarios. Other than in academic benchmark data sets, in our scenario each assembled part is allowed to contain flexible fastening elements and the number of assembled parts is quite high. With our framework we are able to derive a meaningful assembly priority graph for the parts. Our framework divides the disassembly motion of each part into a NEAR- and a subsequent FAR planning phase and uses existing specialized motion planners for each phase. To reduce the number of unsuccessful motion planning requests we use a general Voronoi diagram graph and a novel collision perceiving method which significantly speed up our framework. At the end, we create an assembly priority graph to indicate which parts must be disassembled before others. In our experiments, we show that our framework is the first one which is able to generate a priority graph for a representative data set from the automotive industry. Moreover, the reported disassembly motions for the individual parts are shorter and can be computed faster than with other state-of-the-art frameworks.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116591589","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 : 2022-05-23DOI: 10.1109/icra46639.2022.9812377
Hiroyuki Hayashi, Toshihiro Kawase, Tetsuro Miyazaki, Maina Sogabe, Y. Nakajima, K. Kawashima
Wearable gait assistive devices have been im-proved by soft robotics in terms of safety and physical burden of the wearer. Currently, electrical sensors and computers around the wearer are bottlenecks in enhancing the wearer's activities. In this paper, we present a wearable gait assistive system using soft pneumatic system for all the actuation, sensing, and computation. Pneumatic artifical muscles (PAMs) on the thighs were used to generate assistance force, and thin PAMs on the whole legs were used for sensing the wearer's motion. All thin PAMs were connected to each other by tubes, and the pressure response in the tubes were exploited to compute the wearer's motion in manner of physical reservoir computing. The left thigh angular velocity estimated from the reservoir response was used for control the PAMs for actuation. Our experiment with the use of gait assistance showed that the system worked correctly. This paper shows that the pneumatic analog computation system for sensing soft body can help the functionality of soft wearable assistive devices.
{"title":"Online Assistance Control of a Pneumatic Gait Assistive Suit Using Physical Reservoir Computing Exploiting Air Dynamics","authors":"Hiroyuki Hayashi, Toshihiro Kawase, Tetsuro Miyazaki, Maina Sogabe, Y. Nakajima, K. Kawashima","doi":"10.1109/icra46639.2022.9812377","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9812377","url":null,"abstract":"Wearable gait assistive devices have been im-proved by soft robotics in terms of safety and physical burden of the wearer. Currently, electrical sensors and computers around the wearer are bottlenecks in enhancing the wearer's activities. In this paper, we present a wearable gait assistive system using soft pneumatic system for all the actuation, sensing, and computation. Pneumatic artifical muscles (PAMs) on the thighs were used to generate assistance force, and thin PAMs on the whole legs were used for sensing the wearer's motion. All thin PAMs were connected to each other by tubes, and the pressure response in the tubes were exploited to compute the wearer's motion in manner of physical reservoir computing. The left thigh angular velocity estimated from the reservoir response was used for control the PAMs for actuation. Our experiment with the use of gait assistance showed that the system worked correctly. This paper shows that the pneumatic analog computation system for sensing soft body can help the functionality of soft wearable assistive devices.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129729510","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 : 2022-05-23DOI: 10.1109/icra46639.2022.9812281
Vishal Bhutani, A. Majumder, M. Vankadari, S. Dutta, Aaditya Asati, Swagat Kumar
The ability to apply a previously-learned skill (e.g., pushing) to a new task (context or object) is an important requirement for new-age robots. An attempt is made to solve this problem in this paper by proposing a deep meta-imitation learning framework comprising of an attentive-embedding net-work and a control network, capable of learning a new task in an end-to-end manner while requiring only one or a few visual demonstrations. The feature embeddings learnt by incorporating spatial attention is shown to provide higher embedding and control accuracy compared to other state-of-the-art methods such as TecNet [7] and MIL [4]. The interaction between the embedding and the control networks is improved by using multiplicative skip-connections and is shown to overcome the overfitting of the trained model. The superiority of the proposed model is established through rigorous experimentation using a publicly available dataset and a new dataset created using PyBullet [36]. Several ablation studies have been carried out to justify the design choices.
{"title":"Attentive One-Shot Meta-Imitation Learning From Visual Demonstration","authors":"Vishal Bhutani, A. Majumder, M. Vankadari, S. Dutta, Aaditya Asati, Swagat Kumar","doi":"10.1109/icra46639.2022.9812281","DOIUrl":"https://doi.org/10.1109/icra46639.2022.9812281","url":null,"abstract":"The ability to apply a previously-learned skill (e.g., pushing) to a new task (context or object) is an important requirement for new-age robots. An attempt is made to solve this problem in this paper by proposing a deep meta-imitation learning framework comprising of an attentive-embedding net-work and a control network, capable of learning a new task in an end-to-end manner while requiring only one or a few visual demonstrations. The feature embeddings learnt by incorporating spatial attention is shown to provide higher embedding and control accuracy compared to other state-of-the-art methods such as TecNet [7] and MIL [4]. The interaction between the embedding and the control networks is improved by using multiplicative skip-connections and is shown to overcome the overfitting of the trained model. The superiority of the proposed model is established through rigorous experimentation using a publicly available dataset and a new dataset created using PyBullet [36]. Several ablation studies have been carried out to justify the design choices.","PeriodicalId":341244,"journal":{"name":"2022 International Conference on Robotics and Automation (ICRA)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128385831","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：