Pub Date : 2021-07-16DOI: 10.1109/HUMANOIDS47582.2021.9555781
Elisa Maiettini, V. Tikhanoff, L. Natale
Reliable perception and efficient adaptation to novel conditions are priority skills for humanoids that function in dynamic environments. The vast advancements in latest computer vision research, brought by deep learning methods, are appealing for the robotics community. However, their adoption in applied domains is not straightforward since adapting them to new tasks is strongly demanding in terms of annotated data and optimization time. Nevertheless, robotic platforms, and especially humanoids, present opportunities (such as additional sensors and the chance to explore the environment) that can be exploited to overcome these issues.In this paper, we present a pipeline for efficiently training an object detection system on a humanoid robot. The proposed system allows to iteratively adapt an object detection model to novel scenarios, by exploiting: (i) a teacher-learner pipeline, (ii) weakly supervised learning techniques to reduce the human labeling effort and (iii) an on-line learning approach for fast model re-training. We use the R1 humanoid robot for both testing the proposed pipeline in a real-time application and acquire sequences of images to benchmark the method. We made the code of the application publicly available.
{"title":"Weakly-Supervised Object Detection Learning through Human-Robot Interaction","authors":"Elisa Maiettini, V. Tikhanoff, L. Natale","doi":"10.1109/HUMANOIDS47582.2021.9555781","DOIUrl":"https://doi.org/10.1109/HUMANOIDS47582.2021.9555781","url":null,"abstract":"Reliable perception and efficient adaptation to novel conditions are priority skills for humanoids that function in dynamic environments. The vast advancements in latest computer vision research, brought by deep learning methods, are appealing for the robotics community. However, their adoption in applied domains is not straightforward since adapting them to new tasks is strongly demanding in terms of annotated data and optimization time. Nevertheless, robotic platforms, and especially humanoids, present opportunities (such as additional sensors and the chance to explore the environment) that can be exploited to overcome these issues.In this paper, we present a pipeline for efficiently training an object detection system on a humanoid robot. The proposed system allows to iteratively adapt an object detection model to novel scenarios, by exploiting: (i) a teacher-learner pipeline, (ii) weakly supervised learning techniques to reduce the human labeling effort and (iii) an on-line learning approach for fast model re-training. We use the R1 humanoid robot for both testing the proposed pipeline in a real-time application and acquire sequences of images to benchmark the method. We made the code of the application publicly available.","PeriodicalId":320510,"journal":{"name":"2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130307102","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 : 2021-07-15DOI: 10.1109/HUMANOIDS47582.2021.9555780
Italo Belli, Matteo Parigi Polverini, Arturo Laurenzi, E. Hoffman, P. Rocco, N. Tsagarakis
This paper presents a trajectory optimization approach to the motion generation problem of hybrid locomotion strategies for a wheeled-legged quadrupedal robot with steerable wheels. To this end, traditional Single Rigid Body Dynamics has been employed and extended by adding a unicycle model for each leg, conveniently incorporating the nonholonomic rolling constraints. The proposed approach can generate hybrid locomotion strategies as well as pure driving and legged locomotion with minimum effort for the user. The effectiveness of the proposed approach has been experimentally validated on the humanoid quadruped CENTAURO, employing a hierarchical inverse kinematics engine to track the planned motions.
{"title":"Optimization-Based Quadrupedal Hybrid Wheeled-Legged Locomotion","authors":"Italo Belli, Matteo Parigi Polverini, Arturo Laurenzi, E. Hoffman, P. Rocco, N. Tsagarakis","doi":"10.1109/HUMANOIDS47582.2021.9555780","DOIUrl":"https://doi.org/10.1109/HUMANOIDS47582.2021.9555780","url":null,"abstract":"This paper presents a trajectory optimization approach to the motion generation problem of hybrid locomotion strategies for a wheeled-legged quadrupedal robot with steerable wheels. To this end, traditional Single Rigid Body Dynamics has been employed and extended by adding a unicycle model for each leg, conveniently incorporating the nonholonomic rolling constraints. The proposed approach can generate hybrid locomotion strategies as well as pure driving and legged locomotion with minimum effort for the user. The effectiveness of the proposed approach has been experimentally validated on the humanoid quadruped CENTAURO, employing a hierarchical inverse kinematics engine to track the planned motions.","PeriodicalId":320510,"journal":{"name":"2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125954735","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 : 2021-04-19DOI: 10.1109/HUMANOIDS47582.2021.9555782
Matthew Chignoli, Donghyun Kim, Elijah Stanger-Jones, Sangbae Kim
Demonstrating acrobatic behavior of a humanoid robot such as flips and spinning jumps requires systematic approaches across hardware design, motion planning, and control. In this paper, we present a new humanoid robot design, an actuator-aware kino-dynamic motion planner, and a landing controller as part of a practical system design for highly dynamic motion control of the humanoid robot. To achieve the impulsive motions, we develop two new proprioceptive actuators. The actuator’s torque, velocity, and power limits are reflected in our kino-dynamic motion planner by approximating the configuration-dependent reaction force limits. For the landing control, we effectively integrate model-predictive control and whole-body impulse control by connecting them in a dynamically consistent way to accomplish both the long-time horizon optimal control and high-bandwidth full-body dynamics-based feedback. With the carefully designed hardware and control framework, we successfully demonstrate dynamic behaviors such as back flips, front flips, and spinning jumps in our realistic dynamics simulation.
{"title":"The MIT Humanoid Robot: Design, Motion Planning, and Control For Acrobatic Behaviors","authors":"Matthew Chignoli, Donghyun Kim, Elijah Stanger-Jones, Sangbae Kim","doi":"10.1109/HUMANOIDS47582.2021.9555782","DOIUrl":"https://doi.org/10.1109/HUMANOIDS47582.2021.9555782","url":null,"abstract":"Demonstrating acrobatic behavior of a humanoid robot such as flips and spinning jumps requires systematic approaches across hardware design, motion planning, and control. In this paper, we present a new humanoid robot design, an actuator-aware kino-dynamic motion planner, and a landing controller as part of a practical system design for highly dynamic motion control of the humanoid robot. To achieve the impulsive motions, we develop two new proprioceptive actuators. The actuator’s torque, velocity, and power limits are reflected in our kino-dynamic motion planner by approximating the configuration-dependent reaction force limits. For the landing control, we effectively integrate model-predictive control and whole-body impulse control by connecting them in a dynamically consistent way to accomplish both the long-time horizon optimal control and high-bandwidth full-body dynamics-based feedback. With the carefully designed hardware and control framework, we successfully demonstrate dynamic behaviors such as back flips, front flips, and spinning jumps in our realistic dynamics simulation.","PeriodicalId":320510,"journal":{"name":"2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids)","volume":"312 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125542859","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 : 2021-03-03DOI: 10.1109/HUMANOIDS47582.2021.9555796
Ashwin Khadke, H. Geyer
Numerically computing global policies to optimal control problems for complex dynamical systems is mostly intractable. In consequence, a number of approximation methods have been developed. However, none of the current methods can quantify how much the resulting control underperforms the elusive globally optimal solution. Here we propose policy decomposition, an approximation method with explicit suboptimality estimates. Our method decomposes the optimal control problem into lower-dimensional subproblems, whose optimal solutions are recombined to build a control policy for the entire system. Many such combinations exist, and we introduce the value error and its LQR and DDP estimates to predict the suboptimality of possible combinations and prioritize the ones that minimize it. Using a cart-pole, a 3-link balancing biped and N-link planar manipulators as example systems, we find that the estimates correctly identify the best combinations, yielding control policies in a fraction of the time it takes to compute the optimal control without a notable sacrifice in closed-loop performance. While more research will be needed to find ways of dealing with the combinatorics of policy decomposition, the results suggest this method could be an effective alternative for approximating optimal control in intractable systems.
{"title":"Policy Decomposition: Approximate Optimal Control with Suboptimality Estimates","authors":"Ashwin Khadke, H. Geyer","doi":"10.1109/HUMANOIDS47582.2021.9555796","DOIUrl":"https://doi.org/10.1109/HUMANOIDS47582.2021.9555796","url":null,"abstract":"Numerically computing global policies to optimal control problems for complex dynamical systems is mostly intractable. In consequence, a number of approximation methods have been developed. However, none of the current methods can quantify how much the resulting control underperforms the elusive globally optimal solution. Here we propose policy decomposition, an approximation method with explicit suboptimality estimates. Our method decomposes the optimal control problem into lower-dimensional subproblems, whose optimal solutions are recombined to build a control policy for the entire system. Many such combinations exist, and we introduce the value error and its LQR and DDP estimates to predict the suboptimality of possible combinations and prioritize the ones that minimize it. Using a cart-pole, a 3-link balancing biped and N-link planar manipulators as example systems, we find that the estimates correctly identify the best combinations, yielding control policies in a fraction of the time it takes to compute the optimal control without a notable sacrifice in closed-loop performance. While more research will be needed to find ways of dealing with the combinatorics of policy decomposition, the results suggest this method could be an effective alternative for approximating optimal control in intractable systems.","PeriodicalId":320510,"journal":{"name":"2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134478972","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 : 2021-01-26DOI: 10.1109/HUMANOIDS47582.2021.9555770
Julian Eßer, Shivesh Kumar, Heiner Peters, Vinzenz Bargsten, J. Gea, Carlos Mastalli, O. Stasse, F. Kirchner
Last decades of humanoid research has shown that humanoids developed for high dynamic performance require a stiff structure and optimal distribution of mass~ inertial properties. Humanoid robots built with a purely tree type architecture tend to be bulky and usually suffer from velocity and force/torque limitations. This paper presents a novel series-parallel hybrid humanoid called RH5 which is 2 m tall and weighs only 62.5 kg capable of performing heavy-duty dynamic tasks with 5 kg payloads in each hand. The analysis and control of this humanoid is performed with whole-body trajectory optimization technique based on differential dynamic programming (DDP). Additionally, we present an improved contact stability soft-constrained DDP algorithm which is able to generate physically consistent walking trajectories for the humanoid that can be tracked via a simple PD position control in a physics simulator. Finally, we showcase preliminary experimental results on the RH5 humanoid robot.
{"title":"Design, analysis and control of the series-parallel hybrid RH5 humanoid robot","authors":"Julian Eßer, Shivesh Kumar, Heiner Peters, Vinzenz Bargsten, J. Gea, Carlos Mastalli, O. Stasse, F. Kirchner","doi":"10.1109/HUMANOIDS47582.2021.9555770","DOIUrl":"https://doi.org/10.1109/HUMANOIDS47582.2021.9555770","url":null,"abstract":"Last decades of humanoid research has shown that humanoids developed for high dynamic performance require a stiff structure and optimal distribution of mass~ inertial properties. Humanoid robots built with a purely tree type architecture tend to be bulky and usually suffer from velocity and force/torque limitations. This paper presents a novel series-parallel hybrid humanoid called RH5 which is 2 m tall and weighs only 62.5 kg capable of performing heavy-duty dynamic tasks with 5 kg payloads in each hand. The analysis and control of this humanoid is performed with whole-body trajectory optimization technique based on differential dynamic programming (DDP). Additionally, we present an improved contact stability soft-constrained DDP algorithm which is able to generate physically consistent walking trajectories for the humanoid that can be tracked via a simple PD position control in a physics simulator. Finally, we showcase preliminary experimental results on the RH5 humanoid robot.","PeriodicalId":320510,"journal":{"name":"2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115023602","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 : 2020-09-19DOI: 10.1109/HUMANOIDS47582.2021.9555670
Nils Keunecke, S. Kasaei
As a consequence of an ever-increasing number of service robots, there is a growing demand for highly accurate real-time 3D object recognition. Considering the expansion of robot applications in more complex and dynamic environments, it is evident that it is not possible to pre-program all object categories and anticipate all exceptions in advance. Therefore, robots should have the functionality to learn about new object categories in an open-ended fashion while working in the environment. Towards this goal, we propose a deep transfer learning approach to generate a scale- and pose-invariant object representation by considering shape and texture information in multiple color spaces. The obtained global object representation is then fed to an instance-based object category learning and recognition, where a non-expert human user exists in the learning loop and can interactively guide the process of experience acquisition by teaching new object categories, or by correcting insufficient or erroneous categories. In this work, shape information encodes the common patterns of all categories, while texture information is used to describes the appearance of each instance in detail. Multiple color space combinations and network architectures are evaluated to find the most descriptive system. Experimental results showed that the proposed network architecture outperformed the selected state-of-the-art in terms of object classification accuracy and scalability. Furthermore, we performed a real robot experiment in the context of serve_a_beer scenario to show the real-time performance of the proposed approach.
{"title":"Open-Ended Fine-Grained 3D Object Categorization by Combining Shape and Texture Features in Multiple Colorspaces","authors":"Nils Keunecke, S. Kasaei","doi":"10.1109/HUMANOIDS47582.2021.9555670","DOIUrl":"https://doi.org/10.1109/HUMANOIDS47582.2021.9555670","url":null,"abstract":"As a consequence of an ever-increasing number of service robots, there is a growing demand for highly accurate real-time 3D object recognition. Considering the expansion of robot applications in more complex and dynamic environments, it is evident that it is not possible to pre-program all object categories and anticipate all exceptions in advance. Therefore, robots should have the functionality to learn about new object categories in an open-ended fashion while working in the environment. Towards this goal, we propose a deep transfer learning approach to generate a scale- and pose-invariant object representation by considering shape and texture information in multiple color spaces. The obtained global object representation is then fed to an instance-based object category learning and recognition, where a non-expert human user exists in the learning loop and can interactively guide the process of experience acquisition by teaching new object categories, or by correcting insufficient or erroneous categories. In this work, shape information encodes the common patterns of all categories, while texture information is used to describes the appearance of each instance in detail. Multiple color space combinations and network architectures are evaluated to find the most descriptive system. Experimental results showed that the proposed network architecture outperformed the selected state-of-the-art in terms of object classification accuracy and scalability. Furthermore, we performed a real robot experiment in the context of serve_a_beer scenario to show the real-time performance of the proposed approach.","PeriodicalId":320510,"journal":{"name":"2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids)","volume":"53 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113938961","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 : 2020-05-15DOI: 10.1109/HUMANOIDS47582.2021.9555783
Ahmad Gazar, M. Khadiv, A. Prete, L. Righetti
Linear Model Predictive Control (MPC) has been successfully used for generating feasible walking motions for humanoid robots. However, the effect of uncertainties on constraints satisfaction has only been studied using Robust MPC (RMPC) approaches, which account for the worst-case realization of bounded disturbances at each time instant. In this paper, we propose for the first time to use linear stochastic MPC (SMPC) to account for uncertainties in bipedal walking. We show that SMPC offers more flexibility to the user (or a high level decision maker) by tolerating small (user-defined) probabilities of constraint violation. Therefore, SMPC can be tuned to achieve a constraint satisfaction probability that is arbitrarily close to 100%, but without sacrificing performance as much as tube-based RMPC. We compare SMPC against RMPC in terms of robustness (constraint satisfaction) and performance (optimality). Our results highlight the benefits of SMPC and its interest for the robotics community as a powerful mathematical tool for dealing with uncertainties.
{"title":"Stochastic and Robust MPC for Bipedal Locomotion: A Comparative Study on Robustness and Performance","authors":"Ahmad Gazar, M. Khadiv, A. Prete, L. Righetti","doi":"10.1109/HUMANOIDS47582.2021.9555783","DOIUrl":"https://doi.org/10.1109/HUMANOIDS47582.2021.9555783","url":null,"abstract":"Linear Model Predictive Control (MPC) has been successfully used for generating feasible walking motions for humanoid robots. However, the effect of uncertainties on constraints satisfaction has only been studied using Robust MPC (RMPC) approaches, which account for the worst-case realization of bounded disturbances at each time instant. In this paper, we propose for the first time to use linear stochastic MPC (SMPC) to account for uncertainties in bipedal walking. We show that SMPC offers more flexibility to the user (or a high level decision maker) by tolerating small (user-defined) probabilities of constraint violation. Therefore, SMPC can be tuned to achieve a constraint satisfaction probability that is arbitrarily close to 100%, but without sacrificing performance as much as tube-based RMPC. We compare SMPC against RMPC in terms of robustness (constraint satisfaction) and performance (optimality). Our results highlight the benefits of SMPC and its interest for the robotics community as a powerful mathematical tool for dealing with uncertainties.","PeriodicalId":320510,"journal":{"name":"2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121001896","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 : 2019-09-13DOI: 10.1109/HUMANOIDS47582.2021.9555769
Miguel Arduengo, Ana Arduengo, Adrià Colomé, J. Lobo-Prat, C. Torras
Transferring human motion to a mobile robotic manipulator and ensuring safe physical human-robot interaction are crucial steps towards automating complex manipulation tasks in human-shared environments. In this work, we present a novel human to robot whole-body motion transfer framework. We propose a general solution to the correspondence problem, namely a mapping between the observed human posture and the robot one. For achieving real-time imitation and effective redundancy resolution, we use the whole-body control paradigm, proposing a specific task hierarchy, and present a differential drive control algorithm for the wheeled robot base. To ensure safe physical human-robot interaction, we propose a novel variable admittance controller that stably adapts the dynamics of the end-effector to switch between stiff and compliant behaviors. We validate our approach through several real-world experiments with the TIAGo robot. Results show effective real-time imitation and dynamic behavior adaptation. This constitutes an easy way for a non-expert to transfer a manipulation skill to an assistive robot.
{"title":"Human to Robot Whole-Body Motion Transfer","authors":"Miguel Arduengo, Ana Arduengo, Adrià Colomé, J. Lobo-Prat, C. Torras","doi":"10.1109/HUMANOIDS47582.2021.9555769","DOIUrl":"https://doi.org/10.1109/HUMANOIDS47582.2021.9555769","url":null,"abstract":"Transferring human motion to a mobile robotic manipulator and ensuring safe physical human-robot interaction are crucial steps towards automating complex manipulation tasks in human-shared environments. In this work, we present a novel human to robot whole-body motion transfer framework. We propose a general solution to the correspondence problem, namely a mapping between the observed human posture and the robot one. For achieving real-time imitation and effective redundancy resolution, we use the whole-body control paradigm, proposing a specific task hierarchy, and present a differential drive control algorithm for the wheeled robot base. To ensure safe physical human-robot interaction, we propose a novel variable admittance controller that stably adapts the dynamics of the end-effector to switch between stiff and compliant behaviors. We validate our approach through several real-world experiments with the TIAGo robot. Results show effective real-time imitation and dynamic behavior adaptation. This constitutes an easy way for a non-expert to transfer a manipulation skill to an assistive robot.","PeriodicalId":320510,"journal":{"name":"2020 IEEE-RAS 20th International Conference on Humanoid Robots (Humanoids)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126070267","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：