5 papers
CounterScene: Counterfactual Causal Reasoning in Generative World Models for Safety-Critical Closed-Loop Evaluation
Bowen Jing, Ruiyang Hao, Weitao Zhou +1
Generating safety-critical driving scenarios requires understanding why dangerous interactions arise, rather than merely forcing collisions. However, existing methods rely on heuri…
ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction
Haibao Yu, Kuntao Xiao, Jiahang Wang +7
High-fidelity visual reconstruction and novel-view synthesis are essential for realistic closed-loop evaluation in autonomous driving. While 4D Gaussian Splatting (4DGS) offers a p…
DriveE2E: Closed-Loop Benchmark for End-to-End Autonomous Driving through Real-to-Simulation
Haibao Yu, Wenxian Yang, Ruiyang Hao +4
Closed-loop evaluation is increasingly critical for end-to-end autonomous driving. Current closed-loop benchmarks using the CARLA simulator rely on manually configured traffic scen…
Research Challenges and Progress in the End-to-End V2X Cooperative Autonomous Driving Competition
Ruiyang Hao, Haibao Yu, Jiaru Zhong +16
With the rapid advancement of autonomous driving technology, vehicle-to-everything (V2X) communication has emerged as a key enabler for extending perception range and enhancing dri…
StyleDrive: Towards Driving-Style Aware Benchmarking of End-To-End Autonomous Driving
Ruiyang Hao, Bowen Jing, Haibao Yu +1
Personalization, while extensively studied in conventional autonomous driving pipelines, has been largely overlooked in the context of end-to-end autonomous driving (E2EAD), despit…