Map-Agnostic And Interactive Safety-Critical Scenario Generation via Multi-Objective Tree Search

2026-03-04

AI Summary

This work addresses the challenge of generating safety-critical traffic scenarios that simultaneously exhibit realism, diversity, and plausible interaction logic. The authors propose a multi-objective Monte Carlo Tree Search (MCTS)-based framework that unifies trajectory feasibility and naturalistic driving behavior into a single optimization objective. By integrating SUMO microscopic simulation with OpenStreetMap geospatial data, the approach enables map-agnostic construction of highly complex interactive scenarios. A novel hybrid UCB/LCB (Upper Confidence Bound/Lower Confidence Bound) search strategy is introduced to balance exploration efficiency with risk aversion. Evaluated across four high-risk zones, the method achieves an 85% collision triggering rate while producing trajectories that excel in feasibility and comfort metrics. Moreover, the generated scenarios demonstrate significantly enhanced complexity, as evidenced by increased vehicle mileage and associated CO₂ emissions.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

Generating safety-critical scenarios is essential for validating the robustness of autonomous driving systems, yet existing methods often struggle to produce collisions that are both realistic and diverse while ensuring explicit interaction logic among traffic participants. This paper presents a novel framework for traffic-flow level safety-critical scenario generation via multi-objective Monte Carlo Tree Search (MCTS). We reframe trajectory feasibility and naturalistic behavior as optimization objectives within a unified evaluation function, enabling the discovery of diverse collision events without compromising realism. A hybrid Upper Confidence Bound (UCB) and Lower Confidence Bound (LCB) search strategy is introduced to balance exploratory efficiency with risk-averse decision-making. Furthermore, our method is map-agnostic and supports interactive scenario generation with each vehicle individually powered by SUMO's microscopic traffic models, enabling realistic agent behaviors in arbitrary geographic locations imported from OpenStreetMap. We validate our approach across four high-risk accident zones in Hong Kong's complex urban environments. Experimental results demonstrate that our framework achieves an 85\% collision failure rate while generating trajectories with superior feasibility and comfort metrics. The resulting scenarios exhibit greater complexity, as evidenced by increased vehicle mileage and CO\(_2\) emissions. Our work provides a principled solution for stress testing autonomous vehicles through the generation of realistic yet infrequent corner cases at traffic-flow level.

Problem

• safety-critical scenario generation
• autonomous driving validation
• realistic collision scenarios
• traffic interaction logic
• corner case generation

Innovation

• multi-objective MCTS
• map-agnostic scenario generation
• interactive safety-critical scenarios
• microscopic traffic modeling
• collision diversity