Preprint
Sep 2026
MulDP: Multimodal Diffusion Policy for Autonomous Quadruped Parkour Navigation across Complex Terrains
A Multimodal Diffusion Policy (MulDP) is proposed that integrates visual perception with robot proprioception and goal information to generate temporally coherent and anticipatory navigation velocity commands, tightly coupling perception with embodied control to enable robust autonomous navigation.
Kang-Mai Hu, Yue-Qi Zhang, Peng Zhai et al.
· 1 citation