Movement Trend Guidance lifts 3D diffusion policies without explicit trajectories — 72% vs 49% on real robots
dalian-university-of-technology · hf · 2026-09-21
Researchers propose Movement Trend Guidance, giving 3D diffusion policies foresight without explicit plans. The policy learns a compact latent of interaction evolution from a short observation history, supervised at training time by sparse future gripper states; at inference only the latent remains as future-oriented conditioning, plus a gated FiLM branch at the UNet bottleneck.
Adding just 3.52% parameters to DP3, it reaches 62.8% vs 56.1% on 50-task RoboTwin2.0 mixed training, 71.93% vs 37.08% on LIBERO-40, and 72.0% vs 49.0% on five real-robot tasks — showing diffusion policies benefit substantially from anticipating where an interaction is heading.
More from Embodied
- DeformSmith generates physics-grounded deformable assets for robot manipulation — Can Li · 2026-09-21
- RewardAI launches OM-1 robot foundation model trained on human data alone, zero-shot across arms and humanoids — zipengfu · 2026-09-21
- Tsinghua's EMERGE-Policy dispatches role-based sub-agents to combine VLA, world models and verifiers — jiqizhixin · 2026-09-21
- First human vs humanoid robot T800 fight opens a new entertainment genre — CyberRobooo · 2026-09-21
- Meta to launch camera-less smart glasses at Connect as privacy backlash grows — Scobleizer · 2026-09-21
- Apple's MintAct unifies GUI agents across mobile, desktop, and web, hitting SOTA 48.9 on OSWorld-Verified — apple · 2026-09-21