Abstract
In this paper, we generated intelligent self-driving policies that minimize the injury severity in unexpected traffic signal violation scenarios at an intersection using the deep reinforcement learning. We provided guidance on reward engineering in terms of the multiplicity of objective function. We used a deep deterministic policy gradient method in the simulated environment to train self-driving agents. We designed two agents, one with a single-objective reward function of collision avoidance and the other with a multi-objective reward function of both collision avoidance and goal-approaching. We evaluated their performances by comparing the percentages of collision avoidance and the average injury severity against those of human drivers and an autonomous emergency braking (AEB) system. The percentage of collision avoidance of our agents were 78.89% higher than human drivers and 84.70% higher than the AEB system. The average injury severity score of our agents were only 8.92% of human drivers and 6.25% of the AEB system.
Highlights
INTRODUCTIONIn [10], they propose a mixed-integer linear program-based urban traffic management scheme for an all connected vehicle environment at an intersection scenario
The result shows that our two agents outperformed both human drivers and the Autonomous Emergency Braking (AEB) system in avoiding unexpected collisions by a statistically significant gap
We synthesized the self-driving policy that minimizes the injury severity when unexpected traffic signal violation accidents occur at an intersection
Summary
In [10], they propose a mixed-integer linear program-based urban traffic management scheme for an all connected vehicle environment at an intersection scenario These studies usually assume a predefined or simplified situation and are not practically applicable in high dimensional and changeable state space like our problem. Using the deep reinforcement learning with only Light Detection and Ranging (LIDAR) observations, we generate intelligent self-driving policies that can avoid the collision or minimize the injury severity in unexpected traffic signal violation scenarios at an intersection. We use a deep deterministic policy gradients method for this optimization problem, which will be explained
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
