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
@article{arxiv.2306.08205,
title = {Agile Catching with Whole-Body MPC and Blackbox Policy Learning},
author = {Saminda Abeyruwan and Alex Bewley and Nicholas M. Boffi and Krzysztof Choromanski and David D'Ambrosio and Deepali Jain and Pannag Sanketi and Anish Shankar and Vikas Sindhwani and Sumeet Singh and Jean-Jacques Slotine and Stephen Tu},
journal= {arXiv preprint arXiv:2306.08205},
year = {2023}
}