PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving

Researchers introduced PlannerForge, a system that uses LLM agents to automate scenario-based testing of motion planners in autonomous driving, according to the paper's description. Scenario-based testing for Autonomous Driving Systems (ADSs) currently remains a fragmented modular pipeline spanning scenario generation, retrieval, modification, ADS execution, and results analysis, which PlannerForge aims to unify. The work targets safety validation of ADS motion planners.

Ensuring the safety of autonomous driving is a critical challenge. Scenario-based testing is a systematic process used to validate Autonomous Driving Systems ADSs , but it remains a fragmented modular pipeline in which scenario generation, retrieval, modification, ADS execution, and results analysi