ManeuverGPT Agentic Control for Safe Autonomous Stunt Maneuvers
This addresses the need for advanced active safety features in autonomous vehicles to handle extreme evasive scenarios, though it is incremental as it builds on existing LLM and simulation technologies.
The paper tackles the problem of enabling autonomous vehicles to perform high-agility stunt maneuvers like J-turns safely, and it demonstrates a novel LLM-based agentic framework called ManeuverGPT that successfully executes these maneuvers in simulation through iterative prompt refinement without retraining.
The next generation of active safety features in autonomous vehicles should be capable of safely executing evasive hazard-avoidance maneuvers akin to those performed by professional stunt drivers to achieve high-agility motion at the limits of vehicle handling. This paper presents a novel framework, ManeuverGPT, for generating and executing high-dynamic stunt maneuvers in autonomous vehicles using large language model (LLM)-based agents as controllers. We target aggressive maneuvers, such as J-turns, within the CARLA simulation environment and demonstrate an iterative, prompt-based approach to refine vehicle control parameters, starting tabula rasa without retraining model weights. We propose an agentic architecture comprised of three specialized agents (1) a Query Enricher Agent for contextualizing user commands, (2) a Driver Agent for generating maneuver parameters, and (3) a Parameter Validator Agent that enforces physics-based and safety constraints. Experimental results demonstrate successful J-turn execution across multiple vehicle models through textual prompts that adapt to differing vehicle dynamics. We evaluate performance via established success criteria and discuss limitations regarding numeric precision and scenario complexity. Our findings underscore the potential of LLM-driven control for flexible, high-dynamic maneuvers, while highlighting the importance of hybrid approaches that combine language-based reasoning with algorithmic validation.