ChatPaper.aiChatPaper

利用全身模型预测控制和黑盒策略学习的敏捷抓取

Agile Catching with Whole-Body MPC and Blackbox Policy Learning

June 14, 2023
作者: Saminda Abeyruwan, Alex Bewley, Nicholas M. Boffi, Krzysztof Choromanski, David D'Ambrosio, Deepali Jain, Pannag Sanketi, Anish Shankar, Vikas Sindhwani, Sumeet Singh, Jean-Jacques Slotine, Stephen Tu
cs.AI

摘要

我们解决了敏捷机器人技术中的一个基准任务:捕捉高速抛掷的物体。这是一个具有挑战性的任务,涉及跟踪、拦截和抱住一个抛掷物体,仅凭视觉观察物体和机器人的本体感知状态,在几分之一秒内完成。我们介绍了两种基本不同解决方案策略的相对优点:(i)使用加速约束轨迹优化的模型预测控制,和(ii)使用零阶优化的强化学习。我们通过大量硬件实验深入探讨了各种性能权衡,包括样本效率、从模拟到真实的转移、对分布变化的稳健性,以及全身多模态。最后,我们提出了融合“经典”和“基于学习”的技术用于敏捷机器人控制的建议。我们的实验视频可在以下网址找到:https://sites.google.com/view/agile-catching
English
We address a benchmark task in agile robotics: catching objects thrown at high-speed. This is a challenging task that involves tracking, intercepting, and cradling a thrown object with access only to visual observations of the object and the proprioceptive state of the robot, all within a fraction of a second. We present the relative merits of two fundamentally different solution strategies: (i) Model Predictive Control using accelerated constrained trajectory optimization, and (ii) Reinforcement Learning using zeroth-order optimization. We provide insights into various performance trade-offs including sample efficiency, sim-to-real transfer, robustness to distribution shifts, and whole-body multimodality via extensive on-hardware experiments. We conclude with proposals on fusing "classical" and "learning-based" techniques for agile robot control. Videos of our experiments may be found at https://sites.google.com/view/agile-catching
PDF81December 15, 2024