Cooperative Lane Changing via Deep Reinforcement Learning

06/20/2019

∙

In this paper, we study how to learn an appropriate lane changing strategy for autonomous vehicles by using deep reinforcement learning. We show that the reward of the system should consider the overall traffic efficiency instead of the travel efficiency of an individual vehicle. In summary, cooperation leads to a more harmonic and efficient traffic system rather than competition

READ FULL TEXT

Cooperative Lane Changing via Deep Reinforcement Learning

Decentralized Cooperative Lane Changing at Freeway Weaving Areas Using Multi-Agent Deep Reinforcement Learning

Facilitating Connected Autonomous Vehicle Operations Using Space-weighted Information Fusion and Deep Reinforcement Learning Based Control

Deep Reinforcement Learning for Shared Autonomous Vehicles (SAV) Fleet Management

Pay to change lanes: A cooperative lane-changing strategy for connected/automated driving

V2I Connectivity-Based Dynamic Queue-Jump Lane for Emergency Vehicles: A Deep Reinforcement Learning Approach

Cooperative Energy and Time-Optimal Lane Change Maneuvers with Minimal Highway Traffic Disruption

Minimally Disruptive Cooperative Lane-change Maneuvers

Cooperative Lane Changing via Deep Reinforcement Learning

Related Research

Decentralized Cooperative Lane Changing at Freeway Weaving Areas Using Multi-Agent Deep Reinforcement Learning

Facilitating Connected Autonomous Vehicle Operations Using Space-weighted Information Fusion and Deep Reinforcement Learning Based Control

Deep Reinforcement Learning for Shared Autonomous Vehicles (SAV) Fleet Management

Pay to change lanes: A cooperative lane-changing strategy for connected/automated driving

V2I Connectivity-Based Dynamic Queue-Jump Lane for Emergency Vehicles: A Deep Reinforcement Learning Approach

Cooperative Energy and Time-Optimal Lane Change Maneuvers with Minimal Highway Traffic Disruption

Minimally Disruptive Cooperative Lane-change Maneuvers