SCP:

Scalable and Customizable Gerneration of Planning-specific
Corner Cases in Autonomous Driving


Lingfeng Zhou 1* ,
Junhao Shi 1* ,
Jin Gao 1 ,
Mohan Jiang 1 ,
Yufeng Liu 1 ,
Yuankai Li 2 ,
and Dequan Wang 1†
* Equal Contribution
Corresponding Author
1 Shanghai Jiao Tong University,
2 Fudan University
2025 IEEE/RSJ International Conference on Intelligent Robots and Systems
Under Review

Corner Cases Generated by SCP-LimSim

Abstract

Autonomous driving systems must reliably handle rare and complex scenarios, known as corner cases, to ensure safety in real-world conditions. However, directly collecting corner case data is often costly, time-consuming, and insufficiently scalable. As a result, researchers have turned to corner case generation methods to address these challenges. Existing methods for planning tasks face three fundamental limitations: (1) weak contextual relevance caused by environment-agnostic generation, (2) poor scalability due to manual scenario engineering, and (3) limited customizability from fixed behavioral templates.

We present SCP, a dual-paradigm framework that synergizes global scenario analysis and individual agent control through Large Language Models (LLMs). Our approach enables scalable generation via top-down coordination of agent trajectories, and customizable behaviors through bottom-up natural language directives, with contextual relevance by language-mediated spatial-temporal reasoning. SCP operates in a data-agnostic, training-free manner through two concrete instantiations.

One is SCP-NuPlan benchmark, with 6,382 challenging scenarios, causing 21.1% performance degradation in state-of-the-art planners. The other is SCP-LimSim simulator, enabling real-time behavior customization via natural language interaction. The proposed framework establishes a new paradigm for safety-critical scenario generation, effectively bridging the gap between algorithmic testing requirements and real-world driving challenges. We will release SCP-NuPlan and SCP-LimSim soon.

SCP provides a scalable and customizable approach utilizing LLMs for generating planning-specific corner cases.
SCP provides a scalable and customizable approach utilizing LLMs for generating planning-specific corner cases. Top: Through the global LLM agent, we build SCP-NuPlan on the existing dataset, using global information to modify vehicle trajectories for scalability. Bottom: Through the individual LLM agent, we build SCP-LimSim on the existing simulator, enabling customization through natural language-based individual control.