Research Analyzer
← Back ICRA 2026

PCASim: Promptable Closed-Loop Adversarial Simulation for Urban Traffic Environment

Chuancheng Zhang, Zhenhao Wang, Kaizheng Li, Yaran Lin, Qiang Guo, Bin Jiang

PDF

AI summary

Key figure (auto-extracted from paper)
A closed-loop simulation framework combining LLMs and reinforcement learning generates highly realistic adversarial driving scenarios that significantly improve autonomous vehicle safety testing.
Adversarial Simulation Autonomous Driving Large Language Models Reinforcement Learning Closed-loop Testing Scenario Generation

Problem

Traditional autonomous driving testing relies on inefficient real-world data or isolated scenario generation methods that fail to integrate data, knowledge, and adversarial approaches, lacking a closed-loop system for co-evolving scenario generation and agent training.

Approach

The authors construct a dynamic adversarial scenario repository from real traffic data and use a retrieval-augmented LLM to convert user prompts into executable simulation code, then train reinforcement learning agents to navigate these scenarios in a continuous feedback loop that enriches the dataset.

Key results

  • Improved domain-specific language generation accuracy by 12%
  • Increased newly generated scenario transformation success rate by 8%
  • Enhanced obstacle-avoidance capability by 30%
  • Constructed a dynamic, retrieval-augmented adversarial scenario repository

Why it matters

It provides autonomous driving developers with a scalable, automated pipeline for generating and validating safety-critical corner cases, accelerating robust model training and reducing reliance on costly real-world testing.

Abstract

Real-world autonomous driving, particularly in urban environments with numerous corner cases, requires rigorous testing to ensure product safety and robustness. How- ever, few studies have explored integrating adversarial scenario generation with the training of safety agents in closed-loop testing, enabling efficient co-evolution and mutual enhancement of both. To address this challenge, an adversarial behavior knowledge repository is constructed by applying rule-based filtering to an open-source dataset, combined with knowledge retrieval modules tailored for simulation environments. A large language model (LLM) is employed to integrate knowledge-, data-, and adversarial-driven approaches, generating safety- critical traffic scenarios customized to user needs. Additionally, while evaluating the generated scenarios, we employ rein- forcement learning models to train the behaviors of different types of vehicles, thereby enriching scenario diversity beyond existing datasets while preserving realism. Experimental results demonstrate that the proposed framework improves the accuracy of domain-specific language generation by 12%. Moreover, the success rate of newly generated scenario transformations increases by 8%, while obstacle-avoidance capability is en- hanced by 30%. For the complete manuscript, please refer to: https://zhenhaooo.github.io/PCASim.github.io/

Index terms

Motion and Path Planning Intelligent Transportation Systems Autonomous Agents

Related papers