5 papers
MomADv2: Reliable Temporal Memory for End-to-End Autonomous Driving
Ziying Song, Shengkai Zhang, Lin Liu +8
Long-horizon planning is critical for safe autonomous driving in complex scenarios. Existing methods improve planning continuity with temporal memory, but such memory may become in…
Not All History Helps: Velocity-Aware Selective Memory for Long-Horizon End-to-End Autonomous Driving
Yuchen Liu, Ziying Song, Shengkai Zhang +6
Reliable long-horizon planning remains a key challenge in end-to-end autonomous driving. By accounting for future motion evolution and potential consequences, it provides forward-l…
GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving
Ziying Song, Caiyan Jia, Lin Liu +8
End-to-end autonomous driving has made significant progress by unifying perception, prediction, and planning within a single learning framework, achieving strong performance in sho…
GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving
Lin Liu, Caiyan Jia, Guanyi Yu +6
Driving planning is a critical component of end-to-end (E2E) autonomous driving. However, prevailing Imitative E2E Planners often suffer from multimodal trajectory mode collapse, f…
Beyond Imitation: Constraint-Aware Trajectory Generation with Flow Matching For End-to-End Autonomous Driving
Lin Liu, Guanyi Yu, Ziying Song +5
Planning is a critical component of end-to-end autonomous driving. However, prevailing imitation learning methods often suffer from mode collapse, failing to produce diverse trajec…