EUVIMEDSkopri EUVIMED
Open access · CC BY 4.0

DriveTDPA: Trajectory-Decision Preference Alignment for Vision-Language Autonomous Driving Planning

Dingqi Liu, Jiayu Qin

Electronics · 2026-06-01 · 15 (11) · 2378

DOI: 10.3390/electronics15112378 ↗

At a glance

Journal article in Electronics, published online on 2026-06-01. Written by Dingqi Liu and 1 co-authors. 24 references. The full text is freely available (open access, CC BY 4.0).

AstrattDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Autonomous driving planning requires not only accurate trajectory prediction but also coherent semantic alignment across perception, decision making, and motion generation. Existing vision-language-based approaches predominantly focus on improving trajectory accuracy, which may lead to limited behavioral consistency. In this paper, we reformulate planning as a structured autoregressive generation task, where reasoning, actions, and future trajectories are jointly produced from multimodal observations. Based on this formulation, we propose Trajectory-Decision Joint Preference Optimization (TDJPO), which is a rollout-based alignment framework equipped with a unified reward that simultaneously captures physical trajectory quality and decision-level coherence. Starting from a supervised fine-tuned model, we construct preference pairs through stochastic rollouts and optimize the model using direct preference optimization. Experimental results on the NuScenes-TP benchmark demonstrate that our approach consistently enhances both trajectory accuracy and semantic consistency compared with supervised fine tuning, trajectory-only optimization, and lightweight vision-language baselines. These findings emphasize the necessity of jointly aligning physical feasibility and decision-level reasoning for achieving coherent and human-like autonomous driving behavior.

Cite

APA

Liu, D., & Qin, J. (2026). DriveTDPA: Trajectory-Decision Preference Alignment for Vision-Language Autonomous Driving Planning. Electronics, 15(11), 2378. https://doi.org/10.3390/electronics15112378

Vancouver

Liu D, Qin J. DriveTDPA: Trajectory-Decision Preference Alignment for Vision-Language Autonomous Driving Planning. Electronics. 2026;15(11):2378. doi:10.3390/electronics15112378

BibTeX
@article{Liu2026,
  author = {Liu, Dingqi and Qin, Jiayu},
  title = {DriveTDPA: Trajectory-Decision Preference Alignment for Vision-Language Autonomous Driving Planning},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {11},
  pages = {2378},
  doi = {10.3390/electronics15112378}
}
Start for free →