arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.04792cs.RO
收藏

使用真实演示数据学习自主移动性

Learning Autonomous Mobility Using Real Demonstration Data

University of Edinburgh(爱丁堡大学);School of Informatics(信息学院);Institute for Perception, Action, and Behaviour(感知、行动与行为研究所)

Jiacheng Gu, Zhibin Li

摘要:

提出了一种有效的基于学习的框架,从人的遥操作演示中学习反馈控制策略,实现了履带式机器人的越障、楼梯穿越、打滑控制和包裹投递。由于现实世界中的不确定性,如障碍物和滑移,闭环反馈控制在提高鲁棒性和弹性方面发挥着重要作用,但控制律难以手动编程以实现自主行为。我们制定了一个基于长短期记忆(LSTM)神经网络的架构,它可以有效地从人类演示中学习反应式控制策略。使用来自一些真实演示的数据集,我们的算法可以直接学习成功的策略,包括障碍物谈判,爬楼梯和交付,跌倒恢复和滑动的纠正控制。我们提出了复杂机器人动作的分解,以减少学习的长期依赖关系的难度。此外,我们提出了一种方法来有效地处理非最佳演示和学习新技能,因为收集足够的演示可能是耗时的,有时在一个真正的机器人系统上是非常困难的。

英文摘要:

This work proposed an efficient learning-based framework to learn feedback control policies from human teleoperated demonstrations, which achieved obstacle negotiation, staircase traversal, slipping control and parcel delivery for a tracked robot. Due to uncertainties in real-world scenarios, eg obstacle and slippage, closed-loop feedback control plays an important role in improving robustness and resilience, but the control laws are difficult to program manually for achieving autonomous behaviours. We formulated an architecture based on a long-short-term-memory (LSTM) neural network, which effectively learn reactive control policies from human demonstrations. Using datasets from a few real demonstrations, our algorithm can directly learn successful policies, including obstacle-negotiation, stair-climbing and delivery, fall recovery and corrective control of slippage. We proposed decomposition of complex robot actions to reduce the difficulty of learning the long-term dependencies. Furthermore, we proposed a method to efficiently handle non-optimal demos and to learn new skills, since collecting enough demonstration can be time-consuming and sometimes very difficult on a real robotic system.

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。

↑