Date of Award

6-22-2022

Publication Type

Thesis

Degree Name

M.A.Sc.

Department

Civil and Environmental Engineering

Keywords

Cooperative Adaptive Cruise Control;Cooperative System;Deep Learning;Q-learning;Vehicle to Vehicle Communication

Supervisor

Shahpour Alirezaee

Supervisor

Mehrdad Saif

Abstract

This thesis presents a cooperative adaptive cruise control (CACC) system with integrated lidar and vehicle-to-vehicle (V2V) communication. Firstly, an adaptive cruise control system (ACC) is designed for the Q-Car electrical vehicle. Secondly, a CACC system with V2V communication function are designed based on a new algorithm for improving the ACC system traffic capacity performance. Lastly, the CACC agent was trained by Double Deep Q learning (DDQN) and tested. The proposed CACC system improved the stability of the vehicle. Experimental results demonstrate that the CACC system can decrease the average inter-vehicular distance of ACC by 44.74%, with an additional 40.19% when DDQN was utilized. The DDQN system can match the relative distance with the safety distance to have better distance control. In addition to simulation, experimental results on Q-cars have confirmed the same results. By implementing and testing the ACC and CACC system on the ego car, which follows a lead vehicle with an ACC system in a platoon, the CACC system has a better performance both on following the front vehicle speed and minimizing the difference between the safety distance and relative distance. As a result, the traffic capacity of vehicles can be improved. The vehicles communicate with each other through a WiFi module to transmit information with 2 ms latency.

Download

Share

COinS