Driving Decision and Control for Autonomous Lane Change based on Deep Reinforcement Learning

Abstract

We apply Deep Q-network (DQN) with the consideration of safety during the task for deciding whether to conduct the maneuver. Furthermore, we design two similar Deep Q learning frameworks with quadratic approximator for deciding how to select a comfortable gap and just follow the preceding vehicle. Finally, a polynomial lane change trajectory is generated and Pure Pursuit Control is implemented for path tracking. We demonstrate the effectiveness of this framework in simulation, from both the decision-making and control layers. The proposed architecture also has the potential to be extended to other autonomous driving scenarios.

arXiv commentThis Paper has been submitted to ITSC 2019

References in corpus (3)

• Formulation of Deep Reinforcement Learning Architecture Toward Autonomous Driving for On-Ramp Merge
• Reinforcement and Imitation Learning for Diverse Visuomotor Skills
• Efficient Motion Planning for Automated Lane Change based on Imitation Learning and Mixed-Integer Optimization

Cited by in corpus (5)

• Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives
• Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement
• Efficient Connected and Automated Driving System with Multi-agent Graph Reinforcement Learning
• Decentralized Cooperative Lane Changing at Freeway Weaving Areas Using Multi-Agent Deep Reinforcement Learning
• A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles