TeraSim-World: Worldwide Safety-Critical Data Synthesis for End-to-End Autonomous Driving
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908543193448448 |
|---|---|
| author | Wang, Jiawei Sun, Haowei Yan, Xintao Feng, Shuo Gao, Jun Liu, Henry X. |
| author_facet | Wang, Jiawei Sun, Haowei Yan, Xintao Feng, Shuo Gao, Jun Liu, Henry X. |
| contents | Safe and scalable deployment of end-to-end (E2E) autonomous driving requires extensive and diverse data, particularly safety-critical events. Existing data are mostly generated from simulators with a significant sim-to-real gap or collected from on-road testing that is costly and unsafe. This paper presents TeraSim-World, an automated pipeline that synthesizes realistic and geographically diverse safety-critical data for E2E autonomous driving at anywhere in the world. Starting from an arbitrary location, TeraSim-World retrieves real-world maps and traffic demand from geospatial data sources. Then, it simulates agent behaviors from naturalistic driving datasets, and orchestrates diverse adversities to create corner cases. Informed by street views of the same location, it achieves photorealistic, geographically grounded sensor rendering via the frontier video generation model Cosmos-Drive. By bridging agent and sensor simulations, TeraSim-World provides a scalable and critical data synthesis framework for training and evaluation of E2E autonomous driving systems. Codes and videos are available at https://wjiawei.com/terasim-world-web/ . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13164 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TeraSim-World: Worldwide Safety-Critical Data Synthesis for End-to-End Autonomous Driving Wang, Jiawei Sun, Haowei Yan, Xintao Feng, Shuo Gao, Jun Liu, Henry X. Robotics Systems and Control Safe and scalable deployment of end-to-end (E2E) autonomous driving requires extensive and diverse data, particularly safety-critical events. Existing data are mostly generated from simulators with a significant sim-to-real gap or collected from on-road testing that is costly and unsafe. This paper presents TeraSim-World, an automated pipeline that synthesizes realistic and geographically diverse safety-critical data for E2E autonomous driving at anywhere in the world. Starting from an arbitrary location, TeraSim-World retrieves real-world maps and traffic demand from geospatial data sources. Then, it simulates agent behaviors from naturalistic driving datasets, and orchestrates diverse adversities to create corner cases. Informed by street views of the same location, it achieves photorealistic, geographically grounded sensor rendering via the frontier video generation model Cosmos-Drive. By bridging agent and sensor simulations, TeraSim-World provides a scalable and critical data synthesis framework for training and evaluation of E2E autonomous driving systems. Codes and videos are available at https://wjiawei.com/terasim-world-web/ . |
| title | TeraSim-World: Worldwide Safety-Critical Data Synthesis for End-to-End Autonomous Driving |
| topic | Robotics Systems and Control |
| url | https://arxiv.org/abs/2509.13164 |