Model-Based Deep Reinforcement Learning for Energy Efficient Routing of a Connected and Automated Vehicle

David R. Leech and Hwan-Sik Yoon ()
Additional contact information
David R. Leech: Department of Mechanical Engineering, The University of Alabama, Tuscaloosa, AL 35487, USA
Hwan-Sik Yoon: Department of Mechanical Engineering, The University of Alabama, Tuscaloosa, AL 35487, USA

Sustainability, 2025, vol. 17, issue 13, 1-24

Abstract: The emergence of connected and automated vehicles (CAVs) offers promising opportunities to enhance traffic control and improve overall transportation system performance. However, the complexity and dynamic nature of modern traffic networks pose significant challenges for traditional routing methods. To achieve optimal vehicle routing and support sustainable mobility, more adaptive and intelligent strategies are needed. Among recent advancements, model-based deep reinforcement learning has shown exceptional potential in solving complex decision-making problems across various domains. Leveraging this capability, the present study applies a model-based deep reinforcement learning approach to address the energy-efficient routing problem in a simulated CAV environment. The routes recommended by the algorithm are compared to the shortest route calculated by traffic simulation software. The simulation results show a significant improvement in energy efficiency when the vehicle follows the routes suggested by the learning algorithm, even when the vehicle is subjected to new traffic scenarios. In addition, a comparison of the model-based agent with a conventional model-free reinforcement learning agent across varied traffic conditions demonstrates the robustness of the model-based algorithm. This work represents the first application of a model-based deep reinforcement learning algorithm to the energy-efficient routing problem for CAVs. This work also showcases a novel application of the foundational algorithm AlphaGo Zero.

Keywords: energy-efficient vehicle routing; connected and automated vehicle; traffic control system; sustainable mobility; route optimization; deep reinforcement learning; AlphaGo Zero (search for similar items in EconPapers)
JEL-codes: O13 Q Q0 Q2 Q3 Q5 Q56 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2071-1050/17/13/5727/pdf (application/pdf)
https://www.mdpi.com/2071-1050/17/13/5727/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jsusta:v:17:y:2025:i:13:p:5727-:d:1684492

Access Statistics for this article

Sustainability is currently edited by Ms. Alexandra Wu

More articles in Sustainability from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().