LASER: Script Execution by Autonomous Agents for On-demand Traffic Simulation

TL;DR

This work introduces LASER, an innovative framework that leverages large language models (LLMs) to conduct traffic simulations based on natural language inputs and significantly enhances the process of generating ADS training and testing data, addressing the scalability and diversity issues associated with previous simulation models.

Abstract

Autonomous Driving Systems (ADS) require diverse and safety-critical traffic scenarios for effective training and testing, but the existing data generation methods struggle to provide flexibility and scalability. We propose LASER, a novel frame-work that leverage large language models (LLMs) to conduct traffic simulations based on natural language inputs. The framework operates in two stages: it first generates scripts from user-provided descriptions and then executes them using autonomous agents in real time. Validated in the CARLA simulator, LASER successfully generates complex, on-demand driving scenarios, significantly improving ADS training and testing data generation.

Figures (5)

• Figure 1: Framework of LASER
• Figure 2: A case of script generation result. (A: Action T: Termination Condition R: Reason)
• Figure 3: The visualized results for script execution. (* indicate safety-critical tasks)
• Figure 4: The visualized results for script generation.
• Figure 5: The visualized results for additional tasks.