Sora for Intelligent Vehicles: A Step From Constraint-Based Simulation to Artificiofactual Experiments Through Dynamic Visualization

Xumeng Wang, Xiao Xue, Ran Yan, Xingxia Wang, Yining Di, Wei Chen, Fei-Yue Wang

Abstract: Scenario simulation plays an integral role in the development, application, and management of intelligent vehicles. However, planning agents and customizing scenarios for complex systems are laborious, making it challenging to implement high-performance simulations. The striking progress made by Sora, a large-scale text-to-video model, suggests a research opportunity for high-performance simulation through dynamic visualizations. This paper reports the prospective effects of Sora on the scenario simulation of intelligent vehicles. Specifically, we review the achievements of Sora, picture the perspectives of artificiofactual experiments on intelligent vehicles based on the performance of Sora-type techniques, and discuss how far are we now.