Learning to Compose Hierarchical Object-Centric Controllers for Robotic Manipulation
Learning to Compose Hierarchical Object-Centric Controllers for Robotic Manipulation
复制标题
DOI：
--
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Mohit Sharma;Jacky Liang;Jialiang Zhao;A. LaGrassa;and;Oliver Kroemer
中科院分区：
文献类型：
--
作者：
Mohit Sharma;Jacky Liang;Jialiang Zhao;A. LaGrassa;and;Oliver Kroemer
操作任务通常可以分解为并行执行的多个子任务，例如，在与表保持接触的同时将对象滑动到目标姿态。单个子任务可以通过相对于被操作的对象定义的任务轴控制器来实现，并且可以在层次结构中组合一组以对象为中心的控制器。在以前的工作中，这样的组合是手动定义的或从演示中学习的。相比之下，我们建议使用强化学习来动态地组合以对象为中心的分层控制器来完成操作任务。仿真和现实世界的实验表明，所提出的方法如何提高样本效率，零采样泛化到新的测试环境，以及无需微调的模拟到现实的转移。
Manipulation tasks can often be decomposed into multiple subtasks performed in parallel, e.g., sliding an object to a goal pose while maintaining contact with a table. Individual subtasks can be achieved by task-axis controllers defined relative to the objects being manipulated, and a set of object-centric controllers can be combined in an hierarchy. In prior works, such combinations are defined manually or learned from demonstrations. By contrast, we propose using reinforcement learning to dynamically compose hierarchical object-centric controllers for manipulation tasks. Experiments in both simulation and real world show how the proposed approach leads to improved sample efficiency, zero-shot generalization to novel test environments, and simulation-to-reality transfer without fine-tuning.