SD-RouteFusion reports a 16.9% reduction in 8-second average displacement error for ego-trajectory prediction by fusing SD-map routes with camera and kinematics inputs via a dual-hypothesis gated classifier on 480k real-world scenarios.
Is ego status all you need for open-loop end-to-end autonomous driving?
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
Hydra-MDP uses multi-teacher distillation and a multi-head decoder to learn diverse, metric-specific trajectories in an end-to-end autonomous-driving planner, winning the Navsim challenge.
citing papers explorer
-
SD-RouteFusion: Ego-Trajectory Prediction with SD-Map Route Conditioning
SD-RouteFusion reports a 16.9% reduction in 8-second average displacement error for ego-trajectory prediction by fusing SD-map routes with camera and kinematics inputs via a dual-hypothesis gated classifier on 480k real-world scenarios.
-
Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation
Hydra-MDP uses multi-teacher distillation and a multi-head decoder to learn diverse, metric-specific trajectories in an end-to-end autonomous-driving planner, winning the Navsim challenge.