Publication: Deep Reinforcement Learning for Vechicle Platooning Optimization
Loading...
Date
2024
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
ESTIN
Abstract
Automated vehicle platooning has emerged as a significant method for improving
traffic efficiency, reducing fuel consumption, and enhancing road safety. This thesis
investigates the optimization of vehicle platooning using reinforcement learning
techniques, specifically focusing on Deep Q-Networks (DQN) integrated with dueling
networks and prioritized experience replay (PER). A two-layered approach is
employed, where the first layer identifies joinable platoons and evaluates the benefits of
joining them, and the second layer uses reinforcement learning to optimize merging,
lane-changing, and acceleration strategies. The results of the simulation demonstrate
that the proposed method significantly reduces travel time, fuel consumption, and
improves the overall safety of the platooning process. Future work includes extending
the model to mixed traffic environments with both autonomous and human-driven
vehicles, as well as integrating predictive traffic models.
Keywords: Automated vehicle platooning, Deep Q-Networks, Dueling networks,
Prioritized experience replay, Reinforcement learning, Traffic efficiency, Fuel
Description
Automated platooning, a cooperative driving pattern where a group of vehicles moves at a
consensual speed while maintaining a small and nearly constant distance between adjacent
vehicles, has gained increasing attention due to its potential to improve transportation
systems. We explore the optimization of platooning on highways through the application of
reinforcement learning techniques.
Automated vehicle platooning control and optimization have great potential to
revolutionize optimal control through the application of reinforcement learning techniques.
Automated vehicles can learn to negotiate crossings, merge onto highways, navigate
dynamic settings, and optimize their platooning behavior to alleviate congestion and
enhance traffic efficiency by utilizing deep reinforcement learning algorithms (Peng et al.,
2021). Additionally, automated vehicles may coordinate their actions and communicate
with one another through the use of reinforcement learning. This allows the vehicles to
adjust their speed and make real-time decisions, preventing traffic jams at intersections and
ensuring efficient and smooth traffic flow. Vehicles can achieve long-term optimization and
short-term constraint satisfaction by integrating robust model-free reinforcement learning
with model-based techniques, particularly in modeling techniques for self-driving cars