6 papers
LAP: Fast LAtent Diffusion Planner for Autonomous Driving
Jinhao Zhang, Wenlong Xia, Zhexuan Zhou +3
Diffusion models have demonstrated strong capabilities for modeling human-like driving behaviors in autonomous driving, but their iterative sampling process induces substantial lat…
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
Jinhao Zhang, Zhexuan Zhou, Huizhe Li +5
Diffusion-based visuomotor policies perform well in robotic manipulation, yet current methods still inherit image-generation-style decoders and multi-step sampling. We revisit this…
Information Filtering via Variational Regularization for Robot Manipulation
Jinhao Zhang, Wenlong Xia, Yaojia Wang +6
Diffusion-based visuomotor policies built on 3D visual representations have achieved strong performance in learning complex robotic skills. However, most existing methods employ an…
ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision
Wenlong Xia, Jinhao Zhang, Ce Zhang +4
Vision-based imitation learning has enabled impressive robotic manipulation skills, but its reliance on object appearance while ignoring the underlying 3D scene structure leads to…
PocketDP3: Efficient Pocket-Scale 3D Visuomotor Policy
Jinhao Zhang, Zhexuan Zhou, Huizhe Li +5
Recently, 3D vision-based diffusion policies have shown strong capability in learning complex robotic manipulation skills. However, a common architectural mismatch exists in these…
STORM: Spatial-Temporal Iterative Optimization for Reliable Multicopter Trajectory Generation
Jinhao Zhang, Zhexuan Zhou, Wenlong Xia +2
Efficient and safe trajectory planning plays a critical role in the application of quadrotor unmanned aerial vehicles. Currently, the inherent trade-off between constraint complian…