Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning

TL;DR

This paper presents a deep reinforcement learning approach for obstacle avoidance in mobile robots using only monocular camera input, achieving better performance with discrete actions and enhanced robustness through depth prediction.

Contribution

It introduces an end-to-end deep learning method for obstacle avoidance that does not rely on localization or mapping, utilizing predicted depth maps to improve learning.

Findings

Discrete actions outperform continuous controls in maze environments.

Incorporating depth prediction accelerates learning and robustness.

The approach works with raw monocular images without explicit mapping.

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.