9 papers
GSDrive: Reinforcing Driving Policies by Multi-mode Future Trajectory Probing with 3D Gaussian Splatting Environment
Ziang Guo, Chen Min, Xuefeng Zhang +5
End-to-end (E2E) autonomous driving aims to directly map sensory observations to driving actions, but its real-world deployment is hindered by evolving data distributions and the h…
CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
Keyu Chen, Nanfei Ye, Yida Wang +4
Open-loop imitation learning has advanced modern autonomous driving policy architectures, but closed-loop deployment remains vulnerable to policy-induced distribution shift. Existi…
Driving risk emerges from the required two-dimensional joint evasive acceleration
Hao Cheng, Yanbo Jiang, Wenhao Yu +9
Most autonomous driving safety benchmarks use time-to-collision (TTC) to assess risk and guide safe behaviour. However, TTC-based methods treat risk as a one-dimensional closing pr…
SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving
Wenchao Sun, Xuewu Lin, Keyu Chen +4
End-to-end multi-modal planning has been widely adopted to model the uncertainty of driving behavior, typically by scoring candidate trajectories and selecting the optimal one. Exi…
ForSim: Stepwise Forward Simulation for Traffic Policy Fine-Tuning
Keyu Chen, Wenchao Sun, Hao Cheng +2
As the foundation of closed-loop training and evaluation in autonomous driving, traffic simulation still faces two fundamental challenges: covariate shift introduced by open-loop i…
Modified-Emergency Index (MEI): A Criticality Metric for Autonomous Driving in Lateral Conflict
Hao Cheng, Yanbo Jiang, Qingyuan Shi +5
Effective, reliable, and efficient evaluation of autonomous driving safety is essential to demonstrate its trustworthiness. Criticality metrics provide an objective means of assess…