AirCapRL: Autonomous Aerial Human Motion Capture using Deep Reinforcement Learning
Abstract
In this letter, we introduce a deep reinforcement learning (RL) based multi-robot formation controller for the task of autonomous aerial human motion capture (MoCap). We focus on vision-based MoCap, where the objective is to estimate the trajectory of body pose and shape of a single moving person using multiple micro aerial vehicles. State-of-the-art solutions to this problem are based on classical control methods, which depend on hand-crafted system and observation models. Such models are difficult to derive and generalize across different systems. Moreover, the non-linearity and non-convexities of these models lead to sub-optimal controls. In our work, we formulate this problem as a sequential decision making task to achieve the vision-based motion capture objectives, and solve it using a deep neural network-based RL method. We leverage proximal policy optimization (PPO) to train a stochastic decentralized control policy for formation control. The neural network is trained in a parallelized setup in synthetic environments. We performed extensive simulation experiments to validate our approach. Finally, real-robot experiments demonstrate that our policies generalize to real world conditions. Video Link: https://bit.ly/38SJfjo Supplementary: https://bit.ly/3evfo1O
Cite
@article{arxiv.2007.06343,
title = {AirCapRL: Autonomous Aerial Human Motion Capture using Deep Reinforcement Learning},
author = {Rahul Tallamraju and Nitin Saini and Elia Bonetto and Michael Pabst and Yu Tang Liu and Michael J. Black and Aamir Ahmad},
journal= {arXiv preprint arXiv:2007.06343},
year = {2023}
}
Comments
Article accepted for publication in Robotics and Automation Letters (RA-L) and IROS 2020. 8 Pages, 8 figures