DEVELOPING A CONTROLLER FOR AN ADAPTIVE CRUISE CONTROL (ACC) SYSTEM: UTILIZING DEEP REINFORCEMENT LEARNING (DRL) APPROACH

The addition of Adaptive Cruise Control (ACC) to vehicles enables automatic speed adjustments based on traffic conditions after the driver sets the maximum speed, freeing them to concentrate on steering. This study is dedicated to the development of a passenger car ACC system using Deep Reinforcement Learning (DRL). A critical aspect of this ACC system is its capability to regulate the distance between vehicles by taking into account preceding and following vehicle speeds. It considers three primary inputs: the memory-stored speed of the following vehicle, the lead time specified by the driver, and the radar-measured distance. By adapting speed in different traffic scenarios, the system contributes to averting potential accidents. This research delves into constructing a controller that utilizes the Deep Deterministic Policy Gradient (DDPG) algorithm and compares its outcomes with those from the DQN algorithm. The DDPG controller supervises the longitudinal control actions of a vehicle, enabling it to execute stopping and moving maneuvers safely and efficiently.