arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.06662cs.ROcs.LG
收藏

保护性政策转移

Protective Policy Transfer

Stanford University(斯坦福大学);Georgia Institute of Technology(佐治亚理工学院)

Wenhao Yu, C. Karen Liu, Greg Turk

摘要:

在训练机器人在不可预测的现实世界环境中操作时,能够将现有技能转移到新的情况是一个关键能力。一个成功的转移算法不仅要尽量减少机器人在新环境中需要收集的样本数量,还要防止机器人在转移过程中损坏自身或周围环境。在这项工作中,我们引入了一个政策转移算法,以适应机器人运动技能,以新的情况下,同时尽量减少严重的故障。我们的算法在训练环境中训练两种控制策略:一种是优化的任务策略,以完成感兴趣的任务,另一种是专门用于防止机器人发生不安全事件(例如摔倒在地)的保护策略。为了决定在执行过程中使用哪个策略,我们在训练环境中学习了一个安全估计器模型,该模型估计机器人的连续安全级别。当与一组阈值一起使用时,安全估计器变成用于在保护策略和任务策略之间切换的分类器。我们评估我们的方法上四个模拟机器人运动问题和二维导航问题,并表明我们的方法可以实现成功的转移到显着不同的环境,同时考虑到机器人的安全性。

英文摘要:

Being able to transfer existing skills to new situations is a key capability when training robots to operate in unpredictable real-world environments. A successful transfer algorithm should not only minimize the number of samples that the robot needs to collect in the new environment, but also prevent the robot from damaging itself or the surrounding environment during the transfer process. In this work, we introduce a policy transfer algorithm for adapting robot motor skills to novel scenarios while minimizing serious failures. Our algorithm trains two control policies in the training environment: a task policy that is optimized to complete the task of interest, and a protective policy that is dedicated to keep the robot from unsafe events (e.g. falling to the ground). To decide which policy to use during execution, we learn a safety estimator model in the training environment that estimates a continuous safety level of the robot. When used with a set of thresholds, the safety estimator becomes a classifier for switching between the protective policy and the task policy. We evaluate our approach on four simulated robot locomotion problems and a 2D navigation problem and show that our method can achieve successful transfer to notably different environments while taking the robot's safety into consideration.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑