Driving Strategy for Vehicles in Lane-Free Traffic Environment Based on Deep Deterministic Policy Gradient and Artificial Forces

This paper proposes a novel driving strategy tor Connected and Automated Vehicles (CAVs) in a lane-free traffic environment. To this end, a combination of artificial forces and a reinforcement learning approach are used. To ensure the safe driving behavior of vehicles, an artificial ellipsoid border is assumed around each vehicle by which the lateral and longitudinal forces are obtained and applied. Furthermore, a longitudinal repulsive force based on a Deep Deterministic Policy Gradient (DDPG) network is exerted on the vehicles to avoid longitudinal collisions. Using this approach, the reaction of vehicles is improved, and vehicles may experience closer longitudinal space gaps allowing higher network throughput. The proposed lane-free driving methodology is implemented in the SUMO traffic simulator to showcase its benefits. Additionally, by implementing typical lane-based scenarios in SUMO with the same road condition and traffic demand as lane-free scenarios, a comparison in terms of average speed and time delay has been drawn between the proposed innovative approach and its conventional counterpart, proving the developed approach's functionality.