DittoGym:学习控制可变形软体机器人
DittoGym: Learning to Control Soft Shape-Shifting Robots
AI总结:
本文研究可重构软体机器人的高维强化学习控制,提出统一动作空间与由粗到细课程,并构建 DittoGym 基准,实现机器人在任务序列中多次自主变形。
摘要:
机器人协同设计是指将机器人的形态与学习到的策略联合优化,以完成特定任务,这是一个新兴研究领域。它对软体机器人尤其具有前景,因为这类机器人适用于新型制造技术,能够实现学习得到的形态和执行器。受自然界以及近期新型机器人设计的启发,我们建议更进一步,探索新颖的可重构机器人,其定义是能够在生命周期内改变自身形态的机器人。我们将可重构软体机器人的控制形式化为一个高维强化学习(RL)问题。我们把形态变化、运动和环境交互统一在同一动作空间中,并引入一种合适的、由粗到细的课程,使我们能够发现可对所得机器人实现细粒度控制的策略。我们还推出了 DittoGym,这是一个面向可重构软体机器人的综合 RL 基准,这些机器人需要通过细粒度形态变化来完成任务。最后,我们在 DittoGym 上评估了所提出的由粗到细算法,并展示了机器人能够学会在一个序列中多次改变形态,这一能力唯有我们的 RL 算法能够实现。更多结果见 https://suninghuang19.github.io/dittogym_page/。
英文摘要:
Robot co-design, where the morphology of a robot is optimized jointly with a learned policy to solve a specific task, is an emerging area of research. It holds particular promise for soft robots, which are amenable to novel manufacturing techniques that can realize learned morphologies and actuators. Inspired by nature and recent novel robot designs, we propose to go a step further and explore the novel reconfigurable robots, defined as robots that can change their morphology within their lifetime. We formalize control of reconfigurable soft robots as a high-dimensional reinforcement learning (RL) problem. We unify morphology change, locomotion, and environment interaction in the same action space, and introduce an appropriate, coarse-to-fine curriculum that enables us to discover policies that accomplish fine-grained control of the resulting robots. We also introduce DittoGym, a comprehensive RL benchmark for reconfigurable soft robots that require fine-grained morphology changes to accomplish the tasks. Finally, we evaluate our proposed coarse-to-fine algorithm on DittoGym and demonstrate robots that learn to change their morphology several times within a sequence, uniquely enabled by our RL algorithm. More results are available at https://suninghuang19.github.io/dittogym_page/.
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。