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

2024/10/21 by Gao, Hao, Wang, Jingyue, Fang, Wenyang +4
#FOS: Computer and information sciences #Multiagent Systems (cs.MA) #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2410.16197

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.

Related

• TrafficSimAgent: A Hierarchical Agent Framework for Autonomous Traffic Simulation with MCP Control
• DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving
• AGENTS-LLM: Augmentative GENeration of Challenging Traffic Scenarios with an Agentic LLM Framework
• Traffic Scene Generation from Natural Language Description for Autonomous Vehicles with Large Language Model
• TARGET: Automated Scenario Generation from Traffic Rules for Testing Autonomous Vehicles via Validated LLM-Guided Knowledge Extraction