The team published their study in Communications in Transportation Research ( https://doi.org/10.26599/COMMTR.2026.9640013 ).
"We design D2B to couple transportation scenarios with the vehicle energy system at every part of the framework, ensuring that battery health assessment reflects real-world usage by vehicle users," says Shiqi (Shawn) Ou, professor at the School of Future Technology at South China University of Technology.
Research on travel behavior and vehicle usage patterns is a common paradigm in the transportation field; however, studies that integrate such behavioral characteristics with electric vehicle energy system, particularly battery systems, remain limited. Some scholars have shown that behavioral heterogeneity can significantly affect battery health in electric vehicles. However, most existing studies focus on extending battery lifetime through powertrain and energy management strategies and rarely isolate or quantify the independent contribution of driving behavior. This gap may lead to an overestimation of the theoretical benefits to battery lifetime and to the underperformance of related strategies in real-world applications.
The research team first constructed a multi-scale dynamic driving environment that integrates battery states, powertrain operation, and vehicle-level driving behavior within a unified modeling framework. Deep reinforcement learning was then used to learn different driving style models that jointly optimize battery health and energy efficiency while satisfying safety constraints. Finally, the framework was validated across multiple scenarios using private vehicle travel data from Los Angeles and New England from the United States, as well as ride-hailing trajectory data from Guangzhou, China.
Multi-scale dynamic driving environment
In the study, the researchers integrated a physics-based powertrain system with the CARLA traffic simulation platform. This environment enables the dynamic evaluation of how driving behavior affects battery aging and energy consumption, providing a foundation for modeling the coupled states of transportation and energy systems.
Driving behavior models
Unlike conventional battery health–aware frameworks based on fixed driving cycles, this study extends the problem formulation to dynamic driving scenarios that incorporate energy efficiency, battery health, and safety.
A Quantitative Assessment of Driving Behavior Impacts on Electric Vehicle Battery Health
Under different travel demands and across different regions, the framework's ten-year battery health estimations are close to those obtained under standard driving cycles.
Quantitative results across different driving behaviors show that more stable driving behavior can extend battery lifetime by approximately 10% over a 10-year time horizon; under high-intensity taxi travel demand, a comparable level of battery degradation may be reached in as little as five years.
"By incorporating physics-based models into the battery health assessment, the framework achieves both strong reliability and high interpretability," says Shiqi (Shawn) Ou, professor at the School of Future Technology at South China University of Technology.
Impact and implications
The authors emphasize that battery lifetime assessment should be integrated with heterogeneous driving behaviors across different drivers.
As the electrification of transportation continues to advance, personalized battery health assessment for electric vehicles will be crucial for strengthening market confidence.
This study provides a practically useful analytical framework for battery health assessment based on travel patterns and behavioral heterogeneity, enabling rapid and simulation-based support for algorithm development and decision-making, battery insurance pricing, and other related intelligent driving or Eco-driving algorithm research in a reliable and interpretable manner.
About Communications in Transportation Research
Communications in Transportation Research was launched in 2021, with academic support provided by Tsinghua University and China Intelligent Transportation Systems Association. The Editors-in-Chief are Professor Xiaobo Qu, a member of the Academia Europaea from Tsinghua University and Professor Xiaopeng (Shaw) Li from University of Wisconsin–Madison. The journal mainly publishes high-quality, original research and review articles that are of significant importance to emerging transportation systems, aiming to serve as an international platform for showcasing and exchanging innovative achievements in transportation and related fields, fostering academic exchange and development between China and the global community.
It has been indexed in SCIE, SSCI, Ei Compendex, Scopus, CSTPCD, CSCD, OAJ, DOAJ, TRID and other databases. It was selected as Q1 Top Journal in the Engineering and Technology category of the Chinese Academy of Sciences (CAS) Journal Ranking List. In 2022, it was selected as a High-Starting-Point new journal project of the "China Science and Technology Journal Excellence Action Plan". In 2024, it was selected as the Support the Development Project of "High-Level International Scientific and Technological Journals". The same year, it was also chosen as an English Journal Tier Project of the "China Science and Technology Journal Excellence Action Plan PhaseⅡ". In 2024, it received the first impact factor (2023 IF) of 12.5, ranking Top1 (1/58, Q1) among all journals in "TRANSPORTATION" category. In 2025, its 2024 IF was announced as 14.5, maintaining the Top1 position (1/62, Q1) in the same category.
From Volume 6 (2026), Communications in Transportation Research will be published by Tsinghua University Press on the SciOpen platform with the official journal website at https://www.sciopen.com/journal/2097-5023 . We kindly request that all new manuscript submissions be made through the journal's submission system at https://mc03.manuscriptcentral.com/commtr
