# TeraSim: Uncovering Unknown Unsafe Events for Autonomous Vehicles through Generative Simulation

arXiv: https://arxiv.org/abs/2503.03629 · HTML: https://mlsanity.com/paper/2503.03629/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2025.

## Built on by (most cited first, 6 of 6)

- [Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation](https://mlsanity.com/paper/2603.14948/) (2026)
- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://mlsanity.com/paper/2505.08854/) (2025)
- [TeraSim-World: Worldwide Safety-Critical Data Synthesis for End-to-End Autonomous Driving](https://mlsanity.com/paper/2509.13164/) (2025)
- [RADE: Learning Risk-Adjustable Driving Environment via Multi-Agent Conditional Diffusion](https://mlsanity.com/paper/2505.03178/) (2025)
- [SENSE-VAD: Sentient and Semantic Video Anomaly Detection for Autonomous Driving](https://mlsanity.com/paper/2606.31875/) (2026)
- [WM-Cov: Test Adequacy for Interactive World-Model-Style Autonomous Driving Simulation](https://mlsanity.com/paper/2608.00298/) (2026)

## Abstract (arXiv)

Traffic simulation is essential for autonomous vehicle (AV) development, enabling comprehensive safety evaluation across diverse driving conditions. However, traditional rule-based simulators struggle to capture complex human interactions, while data-driven approaches often fail to maintain long-term behavioral realism or generate diverse safety-critical events. To address these challenges, we propose TeraSim, an open-source, high-fidelity traffic simulation platform designed to uncover unknown unsafe events and efficiently estimate AV statistical performance metrics, such as crash rates. TeraSim is designed for seamless integration with third-party physics simulators and standalone AV stacks, to construct a complete AV simulation system. Experimental results demonstrate its effectiveness in generating diverse safety-critical events involving both static and dynamic agents, identifying hidden deficiencies in AV systems, and enabling statistical performance evaluation. These findings highlight TeraSim's potential as a practical tool for AV safety assessment, benefiting researchers, developers, and policymakers. The code is available at https://github.com/mcity/TeraSim.