Felix Wiebe, Shivesh Kumar, Lasse Shala, S. Vyas, M. Javadi, Frank Kirchner
{"title":"开源双用途 Acrobot 和 Pendubot 平台:欠驱动机器人控制算法基准测试","authors":"Felix Wiebe, Shivesh Kumar, Lasse Shala, S. Vyas, M. Javadi, Frank Kirchner","doi":"10.1109/MRA.2023.3341257","DOIUrl":null,"url":null,"abstract":"Recent interest in the control of underactuated robots has surged significantly due to the impressive athletic behaviors shown by robots developed by, e.g., Boston Dynamics (<uri>https://www.bostondynamics.com</uri>), Agility Robotics (<uri>https://agilityrobotics.com/robots</uri>), and the Massachusetts Institute of Technology <xref ref-type=\"bibr\" rid=\"ref1\">[1]</xref>. This gives rise to the need for canonical robotic hardware setups for studying underactuation and comparing learning and control algorithms for their performance and robustness. Similar to OpenAIGym <xref ref-type=\"bibr\" rid=\"ref2\">[2]</xref> and Stable Baselines <xref ref-type=\"bibr\" rid=\"ref3\">[3]</xref>, which provide simulated benchmarking environments and baselines for reinforcement learning algorithms, there is a need for benchmarking learning and control methods on real canonical hardware setups. To encourage reproducibility in robotics and artificial intelligence research, these hardware setups should be affordable and easy to manufacture with off-the-shelf components, and the accompanying software should be open source. Acrobots and pendubots are classical textbook examples of canonical underactuated systems with strong nonlinear dynamics, and their swing-up and upright balancing is considered a challenging control problem, especially on real hardware.","PeriodicalId":5,"journal":{"name":"ACS Applied Materials & Interfaces","volume":"50 3","pages":"113-124"},"PeriodicalIF":8.3000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Open Source Dual-Purpose Acrobot and Pendubot Platform: Benchmarking Control Algorithms for Underactuated Robotics\",\"authors\":\"Felix Wiebe, Shivesh Kumar, Lasse Shala, S. Vyas, M. Javadi, Frank Kirchner\",\"doi\":\"10.1109/MRA.2023.3341257\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recent interest in the control of underactuated robots has surged significantly due to the impressive athletic behaviors shown by robots developed by, e.g., Boston Dynamics (<uri>https://www.bostondynamics.com</uri>), Agility Robotics (<uri>https://agilityrobotics.com/robots</uri>), and the Massachusetts Institute of Technology <xref ref-type=\\\"bibr\\\" rid=\\\"ref1\\\">[1]</xref>. This gives rise to the need for canonical robotic hardware setups for studying underactuation and comparing learning and control algorithms for their performance and robustness. Similar to OpenAIGym <xref ref-type=\\\"bibr\\\" rid=\\\"ref2\\\">[2]</xref> and Stable Baselines <xref ref-type=\\\"bibr\\\" rid=\\\"ref3\\\">[3]</xref>, which provide simulated benchmarking environments and baselines for reinforcement learning algorithms, there is a need for benchmarking learning and control methods on real canonical hardware setups. To encourage reproducibility in robotics and artificial intelligence research, these hardware setups should be affordable and easy to manufacture with off-the-shelf components, and the accompanying software should be open source. Acrobots and pendubots are classical textbook examples of canonical underactuated systems with strong nonlinear dynamics, and their swing-up and upright balancing is considered a challenging control problem, especially on real hardware.\",\"PeriodicalId\":5,\"journal\":{\"name\":\"ACS Applied Materials & Interfaces\",\"volume\":\"50 3\",\"pages\":\"113-124\"},\"PeriodicalIF\":8.3000,\"publicationDate\":\"2024-06-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"ACS Applied Materials & Interfaces\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1109/MRA.2023.3341257\",\"RegionNum\":2,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MATERIALS SCIENCE, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"ACS Applied Materials & Interfaces","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/MRA.2023.3341257","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 6
摘要
最近,由于波士顿动力公司(https://www.bostondynamics.com)、Agility Robotics 公司(https://agilityrobotics.com/robots)和麻省理工学院(Massachusetts Institute of Technology)等公司开发的机器人表现出令人印象深刻的运动行为,人们对欠驱动机器人控制的兴趣大增[1]。这就需要有典型的机器人硬件设置,用于研究不足行为,并比较学习和控制算法的性能和鲁棒性。OpenAIGym [2] 和 Stable Baselines [3] 为强化学习算法提供了模拟基准环境和基准,与之类似,我们也需要在真实的典型硬件设置上对学习和控制方法进行基准测试。为鼓励机器人和人工智能研究的可重复性,这些硬件装置应价格低廉,易于使用现成部件制造,而且配套软件应开源。杂技机器人和悬挂机器人是教科书上具有强非线性动力学的典型欠驱动系统,它们的摆动和直立平衡被认为是一个具有挑战性的控制问题,尤其是在真实硬件上。
Open Source Dual-Purpose Acrobot and Pendubot Platform: Benchmarking Control Algorithms for Underactuated Robotics
Recent interest in the control of underactuated robots has surged significantly due to the impressive athletic behaviors shown by robots developed by, e.g., Boston Dynamics (https://www.bostondynamics.com), Agility Robotics (https://agilityrobotics.com/robots), and the Massachusetts Institute of Technology [1]. This gives rise to the need for canonical robotic hardware setups for studying underactuation and comparing learning and control algorithms for their performance and robustness. Similar to OpenAIGym [2] and Stable Baselines [3], which provide simulated benchmarking environments and baselines for reinforcement learning algorithms, there is a need for benchmarking learning and control methods on real canonical hardware setups. To encourage reproducibility in robotics and artificial intelligence research, these hardware setups should be affordable and easy to manufacture with off-the-shelf components, and the accompanying software should be open source. Acrobots and pendubots are classical textbook examples of canonical underactuated systems with strong nonlinear dynamics, and their swing-up and upright balancing is considered a challenging control problem, especially on real hardware.
期刊介绍:
ACS Applied Materials & Interfaces is a leading interdisciplinary journal that brings together chemists, engineers, physicists, and biologists to explore the development and utilization of newly-discovered materials and interfacial processes for specific applications. Our journal has experienced remarkable growth since its establishment in 2009, both in terms of the number of articles published and the impact of the research showcased. We are proud to foster a truly global community, with the majority of published articles originating from outside the United States, reflecting the rapid growth of applied research worldwide.