DDPG-Based Energy-Optimal Torque Split Strategy for Dual-Motor Electric Vehicles
SAE International Journal of Vehicle Dynamics, Stability, and NVH · 22.05.2026 · 10 (4)
DOI: 10.4271/10-10-04-0033 ↗Kurz gefasst
Fachartikel in der Zeitschrift SAE International Journal of Vehicle Dynamics, Stability, and NVH, online erschienen am 22.05.2026. Verfasst von Miguel Meléndez-Useros und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This study presents a torque distribution strategy for dual-motor electric vehicles utilizing a Deep Deterministic Policy Gradient reinforcement learning algorithm designed to optimize energy consumption. By using a simplified architecture and replicable reward functions, the proposed agents rely exclusively on standard CAN bus signals, commanded longitudinal force, and the motors’ velocities, eliminating the need for specialized sensors or complex plant models. Two reinforcement agents are trained using two different reward functions: power-based and State of Charge-based. These agents are validated through high-fidelity CarSim–Simulink co-simulations across soft, medium, and severe acceleration scenarios, in which they demonstrate superior performance to traditional adaptive methods. In the most demanding scenario, a typical adaptive strategy achieves an additional 7.8% of power consumption and 85% of optimal energy recovery, while the proposed reinforcement learning strategies reach 0.6% more consumption and 95% energy recovery during braking compared to the theoretical optimum. These results highlight a practical, reliable solution for maximizing efficiency in dual-motor powertrains without significant computational burden on existing electronic control units.
Zitieren
APA
Meléndez-Useros, M., Viadero-Monasterio, F., López-Boada, M. J., & López-Boada, B. (2026). DDPG-Based Energy-Optimal Torque Split Strategy for Dual-Motor Electric Vehicles. SAE International Journal of Vehicle Dynamics, Stability, and NVH, 10(4). https://doi.org/10.4271/10-10-04-0033
Vancouver
Meléndez-Useros M, Viadero-Monasterio F, López-Boada MJ, López-Boada B. DDPG-Based Energy-Optimal Torque Split Strategy for Dual-Motor Electric Vehicles. SAE International Journal of Vehicle Dynamics, Stability, and NVH. 2026;10(4). doi:10.4271/10-10-04-0033
BibTeX
@article{MelndezUseros2026,
author = {Meléndez-Useros, Miguel and Viadero-Monasterio, Fernando and López-Boada, María Jesús and López-Boada, Beatriz},
title = {DDPG-Based Energy-Optimal Torque Split Strategy for Dual-Motor Electric Vehicles},
journal = {SAE International Journal of Vehicle Dynamics, Stability, and NVH},
year = {2026},
volume = {10},
number = {4},
doi = {10.4271/10-10-04-0033}
}
EUVIMED