D-VAT: End-to-End Visual Active Tracking for Micro Aerial Vehicles
Open Access
- 5 April 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (6) , 5046-5053
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 letter 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.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- Exploring Deep Reinforcement Learning for Robust Target Tracking Using Micro Aerial Vehicles2023
- A Benchmark Comparison of Learned Control Policies for Agile Quadrotor Flight2022
- Enhancing continuous control of mobile robots for end-to-end visual active trackingRobotics and Autonomous Systems, 2021
- Neural Topological SLAM for Visual Navigation2020
- SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networks2019
- Stable and Consistent Object Tracking: An Active Vision Approach2018
- A review of quadrotor: An underactuated mechanical systemAnnual Reviews in Control, 2018
- Deep Residual Learning for Image Recognition2016
- Cognitive visual tracking and camera controlComputer Vision and Image Understanding, 2012
- Motion tracking with an active cameraIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994