Autonomous Multi-View Navigation via Deep Reinforcement Learning

In this paper, we propose a novel deep reinforcement learning (DRL) system for the autonomous navigation of mobile robots that consists of three modules: map navigation, multi-view perception and multi-branch control. Our DRL system takes as the input a routed map provided by a global planner and three RGB images captured by a multi-camera setup to gather global and local information, respectively. In particular, we present a multi-view perception module based on an attention mechanism to filter out redundant information caused by multi-camera sensing. We also replace raw RGB images with low-dimensional representations via a specifically designed network, which benefits a more robust sim2real transfer learning. Extensive experiments in both simulated and real-world scenarios demonstrate that our system outperforms state-of-the-art approaches.

Authors

• Xueqin Huang
• Wei Chen
• Wei Zhang 0021
• Ran Song 0001
• Jiyu Cheng
• Yibin Li 0001

Keywords

• Navigation
• Transfer learning
• Reinforcement learning
• Robot sensing systems
• Information filters
• Robustness
• Path planning
• Deep Reinforcement Learning
• Autonomous Navigation
• Deep Learning
• Local Information
• Attention Mechanism
• Raw Images
• Simulation Scenarios
• RGB Images
• Mobile Robot
• Robot Navigation
• Visual Features
• Angular Velocity
• Simulation Environment
• Global Map
• Navigation System
• Linear Velocity
• Real-world Environments
• Markov Decision Process
• Policy Learning
• Obstacle Avoidance
• Deep Reinforcement Learning Agent
• Multiple Cameras
• Unmanned Ground Vehicles
• Proximal Policy Optimization
• Deep Reinforcement Learning Framework
• Direct Perception
• Imitation Learning
• Central View
• Monocular Camera
• Real-world Test