D-VAT: End-to-End Visual Active Tracking for Micro Aerial Vehicles

TL;DR

This paper introduces D-VAT, an end-to-end deep reinforcement learning approach for visual active tracking on micro aerial vehicles, enabling precise, collision-free tracking directly from monocular camera data, with successful real-world deployment.

Contribution

The paper presents a novel deep RL-based method specifically designed for aerial platforms, addressing limitations of existing ground robot tracking approaches.

Findings

Outperforms state-of-the-art baselines in simulation

Enables collision-free and precise tracking

Successfully deployed on real quadrotor platform

Abstract

Visual active tracking is a growing research topic in robotics due to its key role in applications such as human assistance, disaster recovery, and surveillance. In contrast to passive tracking, active tracking approaches combine vision and control capabilities to detect and actively track the target. Most of the work in this area focuses on ground robots, while the very few contributions on aerial platforms still pose important design constraints that limit their applicability. To overcome these limitations, in this paper we propose D-VAT, a novel end-to-end visual active tracking methodology based on deep reinforcement learning that is tailored to micro aerial vehicle platforms. The D-VAT agent computes the vehicle thrust and angular velocity commands needed to track the target by directly processing monocular camera measurements. We show that the proposed approach allows for precise and collision-free tracking operations, outperforming different state-of-the-art baselines on simulated environments which differ significantly from those encountered during training. Moreover, we demonstrate a smooth real-world transition to a quadrotor platform with mixed-reality.