Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning

Wenzel P, Schoen T, Leal-Taixe L, Cremers D (2021)

Publication Type: Conference contribution

Publication year: 2021

Journal

Proceedings - IEEE International Conference on Robotics and Automation Institute of Electrical and Electronics Engineers

Publisher: Institute of Electrical and Electronics Engineers Inc.

Book Volume: 2021-May

Pages Range: 14360-14366

Conference Proceedings Title: Proceedings - IEEE International Conference on Robotics and Automation

Event location: Xi'an, CHN

ISBN: 9781728190778

DOI: 10.1109/ICRA48506.2021.9560787

Abstract

Obstacle avoidance is a fundamental and challenging problem for autonomous navigation of mobile robots. In this paper, we consider the problem of obstacle avoidance in simple 3D environments where the robot has to solely rely on a single monocular camera. In particular, we are interested in solving this problem without relying on localization, mapping, or planning techniques. Most of the existing work consider obstacle avoidance as two separate problems, namely obstacle detection, and control. Inspired by the recent advantages of deep reinforcement learning in Atari games and understanding highly complex situations in Go, we tackle the obstacle avoidance problem as a data-driven end-to-end deep learning approach. Our approach takes raw images as input and generates control commands as output. We show that discrete action spaces are outperforming continuous control commands in terms of expected average reward in maze-like environments. Furthermore, we show how to accelerate the learning and increase the robustness of the policy by incorporating predicted depth maps by a generative adversarial network.

Involved external institutions

Technische Universität München (TUM) DE Germany (DE) Technische Hochschule Ingolstadt DE Germany (DE)

How to cite

APA:

Wenzel, P., Schoen, T., Leal-Taixe, L., & Cremers, D. (2021). Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 14360-14366). Xi'an, CHN: Institute of Electrical and Electronics Engineers Inc..

MLA:

Wenzel, Patrick, et al. "Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning." Proceedings of the 2021 IEEE International Conference on Robotics and Automation, ICRA 2021, Xi'an, CHN Institute of Electrical and Electronics Engineers Inc., 2021. 14360-14366.

BibTeX: Download