arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.09682cs.RO
收藏

刚性与铰接式软体四足机器人高动态运动的两阶段学习

Two-Stage Learning of Highly Dynamic Motions with Rigid and Articulated Soft Quadrupeds

Delft University of Technology(代尔夫特理工大学);German Aerospace Center (DLR)(德国航空航天中心)

Francecso Vezzi, Jiatao Ding, Antonin Raffin, Jens Kober, Cosimo Della Santina

AI总结:

本文提出结合无梯度进化策略与深度强化学习的两阶段框架,无需参考运动即可让刚性及铰接式软体四足机器人从零学会高动态动作,并减少奖励塑造工作量。

摘要:

在四足机器人中受控执行动态运动,尤其是具有铰接式软体身体的机器人,会带来一系列传统方法难以高效应对的独特挑战。在本研究中,我们依靠一个简单而有效的两阶段学习框架来生成四足机器人的动态运动,以解决这些问题。首先,采用无梯度进化策略来发现以简单方式表示的控制策略,从而无需预定义参考运动。随后,我们使用深度强化学习对这些策略进行精调。我们的方法能够有效地从零开始习得 pronking(四足同步跳跃)和后空翻等复杂运动。此外,该方法简化了传统上耗费人力的奖励塑造任务,提高了学习过程的效率。重要的是,我们的框架对铰接式软体四足机器人尤其有效;这类机器人固有的柔顺性和适应性使其非常适合动态任务,但同时也带来了独特的控制挑战。

英文摘要:

Controlled execution of dynamic motions in quadrupedal robots, especially those with articulated soft bodies, presents a unique set of challenges that traditional methods struggle to address efficiently. In this study, we tackle these issues by relying on a simple yet effective two-stage learning framework to generate dynamic motions for quadrupedal robots. First, a gradient-free evolution strategy is employed to discover simply represented control policies, eliminating the need for a predefined reference motion. Then, we refine these policies using deep reinforcement learning. Our approach enables the acquisition of complex motions like pronking and back-flipping, effectively from scratch. Additionally, our method simplifies the traditionally labour-intensive task of reward shaping, boosting the efficiency of the learning process. Importantly, our framework proves particularly effective for articulated soft quadrupeds, whose inherent compliance and adaptability make them ideal for dynamic tasks but also introduce unique control challenges.

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。

↑