Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

End-to-End Vision-Based Adaptive Cruise Control (ACC) Using Deep Reinforcement Learning

Conference ·
DOI:https://doi.org/10.2172/1827205· OSTI ID:1827205

This paper presented a deep reinforcement learning method named Double Deep Q-networks to design an end-to-end vision-based adaptive cruise control (ACC) system. A simulation environment of a highway scene was set up in Unity, which is a game engine that provided both physical models of vehicles and feature data for training and testing. Well-designed reward functions associated with the following distance and throttle/brake force were implemented in the reinforcement learning model for both internal combustion engine (ICE) vehicles and electric vehicles (EV) to perform adaptive cruise control. The gap statistics and total energy consumption are evaluated for different vehicle types to explore the relationship between reward functions and powertrain characteristics. Compared with the traditional radar-based ACC systems or human-in-the-loop simulation, the proposed vision-based ACC system can generate either a better gap regulated trajectory or a smoother speed trajectory depending on the preset reward function. The proposed system can be well adaptive to different speed trajectories of the preceding vehicle and operated in real-time.

Research Organization:
University of California Riverside
Sponsoring Organization:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Transportation Office. Vehicle Technologies Office
DOE Contract Number:
EE0008212
OSTI ID:
1827205
Report Number(s):
DOE-UCR-0008212-4
Country of Publication:
United States
Language:
English

Similar Records

Model Predictive Control-Based Trajectory Shaper for Safe and Efficient Adaptive Cruise Control
Conference · Sun Oct 01 00:00:00 EDT 2023 · OSTI ID:2251638

Vehicular enginee idel speed and cruise control system
Patent · Mon Feb 10 23:00:00 EST 1986 · OSTI ID:5833350

Cruise control method and apparatus for a vehicle with a continuously variable transmission
Patent · Tue Sep 20 00:00:00 EDT 1988 · OSTI ID:6888777