Hengchen Dai — accepted AI-conference papers

2024

DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model

Yuqi Wang, Ke Cheng, Jiawei He, Qitai Wang, Hengchen Dai, Yuntao Chen +2

NeurIPS 2024poster

Driving world models have gained increasing attention due to their ability to model complex physical dynamics. However, their superb modeling capability is yet to be fully unleashed due to the limited video diversity in current driving datasets. We introduce DrivingDojo, the first dataset tailor-mad…

Cited by 7 Source ↗PDF ↗Scholar ↗

2020

UST: Unifying Spatio-Temporal Context for Trajectory Prediction in Autonomous Driving

Hao He, Hengchen Dai, Naiyan Wang

IROS 2020poster

Trajectory prediction has always been a challenging problem for autonomous driving, since it needs to infer the latent intention from the behaviors and interactions from traffic participants. This problem is intrinsically hard, because each participant may behave differently under different environm…

Cited by 27 Source ↗Scholar ↗