Learning Robust Manipulation Strategies with Multimodal State Transition Models and Recovery Heuristics
Learning Robust Manipulation Strategies with Multimodal State Transition Models and Recovery Heuristics
复制标题
使用多模式状态转换模型和恢复启发式学习鲁棒操纵策略
DOI：
10.1109/icra.2019.8793623
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Oliver Kroemer
中科院分区：
文献类型：
--
作者：
Austin S. Wang;Oliver Kroemer
机器人在非结构化环境中执行操作任务时容易出错。因此，需要强有力的政策，不仅要避免错误，还要从错误中恢复过来。我们提出了一个框架，通过建模任务结构和优化选择技能和恢复技能的策略来增加基于接触的操作的鲁棒性。基于任务的接触动力学和观察到的状态转移，建立了多模态转移模型。然后使用强化学习从模型中学习策略。通过使用启发式方法生成恢复技能来扩展操作空间，从而逐步改进策略。对三个模拟操作任务的评估验证了该框架的有效性。该机器人能够在多次接触状态变化和遇到错误的情况下完成任务，将任务的平均成功率从70.0%提高到95.3%。
Robots are prone to making mistakes when performing manipulation tasks in unstructured environments. Robust policies are thus needed to not only avoid mistakes but also to recover from them. We propose a framework for increasing the robustness of contact-based manipulations by modeling the task structure and optimizing a policy for selecting skills and recovery skills. A multimodal state transition model is acquired based on the contact dynamics of the task and the observed transitions. A policy is then learned from the model using reinforcement learning. The policy is incrementally improved by expanding the action space by generating recovery skills with a heuristic. Evaluations on three simulated manipulation tasks demonstrate the effectiveness of the framework. The robot was able to complete the tasks despite multiple contact state changes and errors encountered, increasing the success rate averaged across the tasks from 70.0% to 95.3%.