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

翻译：针对敏捷机器人领域的基准任务——高速抛掷物体的抓取，我们提出解决方案。该任务具有极高挑战性，需在毫秒级时间内仅依赖物体视觉观测及机器人本体感知状态，完成跟踪、拦截并稳妥接住抛掷物体的完整流程。我们对比分析了两种根本性差异化策略的相对优势：(i) 基于加速约束轨迹优化的模型预测控制，与(ii) 采用零阶优化的强化学习方法。通过大量实物实验，从样本效率、仿真-现实迁移能力、分布偏移鲁棒性及全身多模态特性等维度，揭示了不同性能权衡的深层机理。最后，我们提出了融合"经典"与"基于学习"技术的敏捷机器人控制方案构想。实验视频请参阅 https://sites.google.com/view/agile-catching