AirCapRL: Autonomous Aerial Human Motion Capture using Deep Reinforcement Learning

TL;DR

This paper presents a deep reinforcement learning approach for autonomous aerial human motion capture using micro aerial vehicles, outperforming classical control methods and demonstrating successful real-world application.

Contribution

Introduces a novel deep RL-based decentralized control policy for aerial human MoCap, replacing traditional model-based methods with a learnable, generalizable approach.

Findings

The RL controller successfully captures human motion in simulation.

Policies generalize effectively from simulation to real-world environments.

The approach outperforms classical control methods in accuracy and robustness.

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