Deep Reinforcement Learning based Local Planner for UAV Obstacle Avoidance using Demonstration Data

TL;DR

This paper introduces a novel deep reinforcement learning framework that combines imitation learning and TD3 to improve UAV obstacle avoidance, reducing training time and enhancing navigation performance in unknown environments.

Contribution

The paper presents a new learning framework that integrates imitation learning with reinforcement learning using TD3, addressing data efficiency and transfer issues in UAV navigation.

Findings

Enhanced navigation performance in simulation environments

Faster training convergence compared to standard DRL methods

Effective obstacle avoidance using depth camera data

Abstract

In this paper, a deep reinforcement learning (DRL) method is proposed to address the problem of UAV navigation in an unknown environment. However, DRL algorithms are limited by the data efficiency problem as they typically require a huge amount of data before they reach a reasonable performance. To speed up the DRL training process, we developed a novel learning framework which combines imitation learning and reinforcement learning and building upon Twin Delayed DDPG (TD3) algorithm. We newly introduced both policy and Q-value network are learned using the expert demonstration during the imitation phase. To tackle the distribution mismatch problem transfer from imitation to reinforcement learning, both TD-error and decayed imitation loss are used to update the pre-trained network when start interacting with the environment. The performances of the proposed algorithm are demonstrated on the challenging 3D UAV navigation problem using depth cameras and sketched in a variety of simulation environments.