AINeutralarXiv – CS AI · 18h ago6/10
🧠
Latent Diffusion Policy: Shaping Latent Spaces for Diffusion-Based Robotic Manipulation
Researchers introduce Latent Diffusion Policy (LDP), a two-stage framework that simplifies robotic manipulation by separating scene understanding from trajectory generation using a shaped latent space. The method outperforms existing approaches on complex multi-arm coordination tasks and successfully transfers to real-world bimanual robots.