Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Junqiao, Yu, Zhongliang, Zhou, Dong, Shi, Jiaqi, Deng, Runran
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913602605154304
author Wang, Junqiao
Yu, Zhongliang
Zhou, Dong
Shi, Jiaqi
Deng, Runran
author_facet Wang, Junqiao
Yu, Zhongliang
Zhou, Dong
Shi, Jiaqi
Deng, Runran
contents The capability of UAVs for efficient autonomous navigation and obstacle avoidance in complex and unknown environments is critical for applications in agricultural irrigation, disaster relief and logistics. In this paper, we propose the DPRL (Distributed Privileged Reinforcement Learning) navigation algorithm, an end-to-end policy designed to address the challenge of high-speed autonomous UAV navigation under partially observable environmental conditions. Our approach combines deep reinforcement learning with privileged learning to overcome the impact of observation data corruption caused by partial observability. We leverage an asymmetric Actor-Critic architecture to provide the agent with privileged information during training, which enhances the model's perceptual capabilities. Additionally, we present a multi-agent exploration strategy across diverse environments to accelerate experience collection, which in turn expedites model convergence. We conducted extensive simulations across various scenarios, benchmarking our DPRL algorithm against the state-of-the-art navigation algorithms. The results consistently demonstrate the superior performance of our algorithm in terms of flight efficiency, robustness and overall success rate.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06313
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information
Wang, Junqiao
Yu, Zhongliang
Zhou, Dong
Shi, Jiaqi
Deng, Runran
Robotics
Computer Vision and Pattern Recognition
Machine Learning
The capability of UAVs for efficient autonomous navigation and obstacle avoidance in complex and unknown environments is critical for applications in agricultural irrigation, disaster relief and logistics. In this paper, we propose the DPRL (Distributed Privileged Reinforcement Learning) navigation algorithm, an end-to-end policy designed to address the challenge of high-speed autonomous UAV navigation under partially observable environmental conditions. Our approach combines deep reinforcement learning with privileged learning to overcome the impact of observation data corruption caused by partial observability. We leverage an asymmetric Actor-Critic architecture to provide the agent with privileged information during training, which enhances the model's perceptual capabilities. Additionally, we present a multi-agent exploration strategy across diverse environments to accelerate experience collection, which in turn expedites model convergence. We conducted extensive simulations across various scenarios, benchmarking our DPRL algorithm against the state-of-the-art navigation algorithms. The results consistently demonstrate the superior performance of our algorithm in terms of flight efficiency, robustness and overall success rate.
title Vision-Based Deep Reinforcement Learning of UAV Autonomous Navigation Using Privileged Information
topic Robotics
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2412.06313