From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving
This addresses the need for adaptive and semantically relevant scenario repair in autonomous driving, though it appears incremental as it builds on existing LLM and fine-tuning methods.
The paper tackles the problem of improving autonomous driving robustness by efficiently repairing failure cases in challenging scenarios, achieving consistent improvements in key metrics across multiple baselines.
Ensuring robust and generalizable autonomous driving requires not only broad scenario coverage but also efficient repair of failure cases, particularly those related to challenging and safety-critical scenarios. However, existing scenario generation and selection methods often lack adaptivity and semantic relevance, limiting their impact on performance improvement. In this paper, we propose \textbf{SERA}, an LLM-powered framework that enables autonomous driving systems to self-evolve by repairing failure cases through targeted scenario recommendation. By analyzing performance logs, SERA identifies failure patterns and dynamically retrieves semantically aligned scenarios from a structured bank. An LLM-based reflection mechanism further refines these recommendations to maximize relevance and diversity. The selected scenarios are used for few-shot fine-tuning, enabling targeted adaptation with minimal data. Experiments on the benchmark show that SERA consistently improves key metrics across multiple autonomous driving baselines, demonstrating its effectiveness and generalizability under safety-critical conditions.