利用全身模型預測控制和黑盒策略學習的敏捷捕捉

摘要

我們探討敏捷機器人中的一項基準任務：捕捉以高速投擲的物體。這是一項具有挑戰性的任務，涉及跟踪、截取和保護一個被投擲的物體，僅通過對物體的視覺觀察和機器人的本體感知狀態，在幾分之一秒內完成。我們介紹兩種基本不同解決方案策略的相對優點：（i）使用加速受限軌跡優化的模型預測控制，和（ii）使用零階優化的強化學習。我們提供有關各種性能折衷的見解，包括樣本效率、從模擬到實際的轉移、對分布變化的穩健性，以及通過大量硬件實驗實現全身多模態。最後，我們提出將“傳統”和“基於學習”的技術融合用於敏捷機器人控制的建議。我們的實驗視頻可在以下網址找到：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

利用全身模型預測控制和黑盒策略學習的敏捷捕捉

Agile Catching with Whole-Body MPC and Blackbox Policy Learning

摘要

Support