FixDrive: Automatically Repairing Autonomous Vehicle Driving Behaviour for $0.08 per Violation
Yang Sun, Christopher M. Poskitt, Kun Wang, Jun Sun

TL;DR
FixDrive is a framework that analyzes driving records to generate interpretable repairs for autonomous vehicles, improving compliance and safety at a low cost using large language models and a domain-specific language.
Contribution
It introduces FixDrive, a novel system that creates generalizable, interpretable AV behavior repairs from incident data using multimodal large language models and a new behavior specification language.
Findings
Improved AV compliance with traffic laws.
Reduced collision rates in benchmark scenarios.
Low repair cost of $0.08 per violation.
Abstract
Autonomous Vehicles (AVs) are advancing rapidly, with Level-4 AVs already operating in real-world conditions. Current AVs, however, still lag behind human drivers in adaptability and performance, often exhibiting overly conservative behaviours and occasionally violating traffic laws. Existing solutions, such as runtime enforcement, mitigate this by automatically repairing the AV's planned trajectory at runtime, but such approaches lack transparency and should be a measure of last resort. It would be preferable for AV repairs to generalise beyond specific incidents and to be interpretable for users. In this work, we propose FixDrive, a framework that analyses driving records from near-misses or law violations to generate AV driving strategy repairs that reduce the chance of such incidents occurring again. These repairs are captured in {\mu}Drive, a high-level domain-specific language for…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAutonomous Vehicle Technology and Safety
