通过度量强化学习的反应性、任务特定对象操作

Simon Hangl, Emre Ugur, S. Szedmák, J. Piater, A. Ude
{"title":"通过度量强化学习的反应性、任务特定对象操作","authors":"Simon Hangl, Emre Ugur, S. Szedmák, J. Piater, A. Ude","doi":"10.1109/ICAR.2015.7251511","DOIUrl":null,"url":null,"abstract":"In the context of manipulation of dynamical systems, it is not trivial to design controllers that can cope with unpredictable changes in the system being manipulated. For example, in a pouring task, the target cup might start moving or the agent may decide to change the amount of the liquid during action execution. In order to cope with these situations, the robot should smoothly (and timely) change its execution policy based on the requirements of the new situation. In this paper, we propose a robust method that allows the robot to smoothly and successfully react to such changes. The robot first learns a set of execution trajectories that can solve a number of tasks in different situations. When encountered with a novel situation, the robot smoothly adapts its trajectory to a new one that is generated by weighted linear combination of the previously learned trajectories, where the weights are computed using a metric that depends on the task. This task-dependent metric is automatically learned in the state space of the robot, rather than the motor control space, and further optimized using using reinforcement learning (RL) framework. We discuss that our system can learn and model various manipulation tasks such as pouring or reaching; and can successfully react to a wide range of perturbations introduced during task executions. We evaluated our method against ground truth with a synthetic trajectory dataset, and verified it in grasping and pouring tasks with a real robot.","PeriodicalId":432004,"journal":{"name":"2015 International Conference on Advanced Robotics (ICAR)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2015-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":"{\"title\":\"Reactive, task-specific object manipulation by metric reinforcement learning\",\"authors\":\"Simon Hangl, Emre Ugur, S. Szedmák, J. Piater, A. Ude\",\"doi\":\"10.1109/ICAR.2015.7251511\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the context of manipulation of dynamical systems, it is not trivial to design controllers that can cope with unpredictable changes in the system being manipulated. For example, in a pouring task, the target cup might start moving or the agent may decide to change the amount of the liquid during action execution. In order to cope with these situations, the robot should smoothly (and timely) change its execution policy based on the requirements of the new situation. In this paper, we propose a robust method that allows the robot to smoothly and successfully react to such changes. The robot first learns a set of execution trajectories that can solve a number of tasks in different situations. When encountered with a novel situation, the robot smoothly adapts its trajectory to a new one that is generated by weighted linear combination of the previously learned trajectories, where the weights are computed using a metric that depends on the task. This task-dependent metric is automatically learned in the state space of the robot, rather than the motor control space, and further optimized using using reinforcement learning (RL) framework. We discuss that our system can learn and model various manipulation tasks such as pouring or reaching; and can successfully react to a wide range of perturbations introduced during task executions. We evaluated our method against ground truth with a synthetic trajectory dataset, and verified it in grasping and pouring tasks with a real robot.\",\"PeriodicalId\":432004,\"journal\":{\"name\":\"2015 International Conference on Advanced Robotics (ICAR)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2015-07-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"12\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2015 International Conference on Advanced Robotics (ICAR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICAR.2015.7251511\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Advanced Robotics (ICAR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAR.2015.7251511","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 12

摘要

在动态系统操纵的背景下,设计能够处理被操纵系统中不可预测变化的控制器并非易事。例如,在浇注任务中,目标杯子可能开始移动,或者代理可能决定在操作执行期间改变液体的量。为了应对这些情况,机器人应该根据新情况的要求顺利(及时)地改变其执行策略。在本文中,我们提出了一种鲁棒方法,使机器人能够顺利成功地对这些变化做出反应。机器人首先学习一组执行轨迹,可以在不同的情况下解决许多任务。当遇到新情况时,机器人可以平滑地将其轨迹调整为由先前学习轨迹的加权线性组合生成的新轨迹,其中权重使用依赖于任务的度量来计算。这种与任务相关的度量是在机器人的状态空间中自动学习的,而不是在电机控制空间中,并使用强化学习(RL)框架进一步优化。我们讨论了我们的系统可以学习和建模各种操作任务,如浇注或到达;并且能够成功地对任务执行过程中引入的各种干扰做出反应。我们用一个合成的轨迹数据集对我们的方法进行了地面真实情况的评估,并在一个真实的机器人抓取和倾倒任务中进行了验证。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Reactive, task-specific object manipulation by metric reinforcement learning
In the context of manipulation of dynamical systems, it is not trivial to design controllers that can cope with unpredictable changes in the system being manipulated. For example, in a pouring task, the target cup might start moving or the agent may decide to change the amount of the liquid during action execution. In order to cope with these situations, the robot should smoothly (and timely) change its execution policy based on the requirements of the new situation. In this paper, we propose a robust method that allows the robot to smoothly and successfully react to such changes. The robot first learns a set of execution trajectories that can solve a number of tasks in different situations. When encountered with a novel situation, the robot smoothly adapts its trajectory to a new one that is generated by weighted linear combination of the previously learned trajectories, where the weights are computed using a metric that depends on the task. This task-dependent metric is automatically learned in the state space of the robot, rather than the motor control space, and further optimized using using reinforcement learning (RL) framework. We discuss that our system can learn and model various manipulation tasks such as pouring or reaching; and can successfully react to a wide range of perturbations introduced during task executions. We evaluated our method against ground truth with a synthetic trajectory dataset, and verified it in grasping and pouring tasks with a real robot.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信