Competent Autonomous Driving Through Fine Tuning Vision Language Action Models with Symbolic Traffic Rules
Organizations: Connected and Autonomous Vehicles Lab (CAV-Lab), University of Surrey, Guildford, GU2 7XH, UK. · Department of Mechanical and Aerospace Engineering, George Washington University, Washington, DC 20052, USA.
Abstract
Vision-language-action (VLA) models offer a unified approach to perception, reasoning, and control for autonomous driving, but accurate action prediction alone does not establish compliance with traffic regulations. This paper presents a rule-guided VLA framework that incorporates symbolic traffic-rule feedback into policy optimisation. The framework combines supervised fine-tuning on expert demonstrations with reinforcement learning (RL) refinement using a reward that encourages encoded-rule compliance while penalising deviations from expert actions. Selected provisions of the United Kingdom Highway Code are formalised as executable first-order logic rules using PyReason, covering speed adaptation, following distance, and road-user priority. A frozen vision-language model extracts scene predicates, which are combined with vehicle-state information to assess the projected consequences of candidate control actions. Offline evaluation on held-out data collected in the CARLA simulator compares three group-based RL methods. The results show improvements in both action prediction accuracy and encoded-rule compliance over the supervised baseline. The best-performing variant increases the overall rule pass rate from 92.9% to 97.6%, with zero observed violations of the encoded road-user-priority check in the evaluated samples. These findings support symbolic rule feedback as a means of improving VLA policy alignment with explicit traffic-rule criteria.
Figures & tables
| Metric | SFT | GRPO | GDPO | Dr. GRPO |
|---|---|---|---|---|
| Throttle MAE (%) | ||||
| Steer MAE (%) | ||||
| Throttle RMSE (%) | ||||
| Steer RMSE (%) | ||||
| Euclidean MAE (%) | ||||
| Euclidean RMSE (%) |
| Rule | SFT | GRPO | GDPO | Dr. GRPO |
|---|---|---|---|---|
| Safe Speed Rule Score | 0.9200 | 1.0000 | 1.0000 | 1.0000 |
| Safe Distance Rule Score | 0.7468 | 0.7848 | 0.7975 | 0.7975 |
| Hierarchy of Road Users Rule Score | -1.0000 | 0.8820 | 0.8820 | 1.0000 |
| Control Accuracy | Rule Violation Rate | ||||
|---|---|---|---|---|---|
| Rules in Reward | Throttle MAE (%) | Steer MAE (%) | Rule H | Rule 125 | Rule 126 |
| Rule-H + Rule-125 + Rule-126 | |||||
| Rule-125 + Rule-126 | |||||
| Rule-H + Rule-126 | |||||
| Rule-H + Rule-125 | |||||
Autonomous Driving
Autonomous driving develops vehicles that perceive road scenes, predict interactions, and plan and control safe movement with limited or no human input.
See all 570 papers