arXiv:2606.11874v1 Announce Type: new Abstract: With the development of autonomous driving systems, mining high-value, safety-critical, and planning-relevant scenarios from large-scale driving logs has become essential for data-driven evaluation. In this paper, we propose AutoMine, a robust self-refining scenario mining method based on LLMs and VLMs. AutoMine uses semantics-preserving prompt augmentation to reduce LLM prompt sensitivity, combines robust trajectory atomic functions with VLM-based functions to handle perception noise and open-world visual cues, and refines generated code through
The continuous development in autonomous driving necessitates more robust and efficient methods for scenario mining, especially with advancements in LLMs and VLMs.
Sophisticated readers should care as this demonstrates a critical step towards more reliable and safer autonomous driving systems through enhanced data-driven evaluation.
The ability to mine high-value, safety-critical scenarios from massive driving logs will be significantly improved, enabling more rigorous testing and validation of autonomous vehicles.
- · Autonomous Vehicle Developers
- · AI-driven Safety & Validation Services
- · Machine Learning Researchers
- · Automotive Industry
- · Traditional Manual Scenario Generation
- · Less Sophisticated Simulation Tools
Refined autonomous driving systems with improved safety and performance metrics.
Accelerated deployment of autonomous vehicles in more complex environments as testing becomes more comprehensive.
Potentially reduced regulatory hurdles for AVs due to a higher degree of validated safety and predictability.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI