AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

M 2 Diffuser: Diffusion-based Trajectory Optimization for Mobile Manipulation in 3D Scenes

Sixu Yan, Zeyu Zhang, Muzhi Han, Zaijin Wang, Qi Xie, Zhitian Li, Zhehan Li, Hangxin Liu, Xinggang Wang, Song Chun Zhu

TPAMI 2025 · Image generation › Autoregressive and latent generation · approach: Diffusion planning and policies · 26 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add trajectory optimization (guided sampling) to the diffusion planner (ablation)M2Diffuser · Test Set One, graspingsuccess rate (%): 21.95 -> 30.54Improved
add trajectory optimization to the diffusion planner (ablation)M2Diffuser · Test Set One, placementsuccess rate (%): 4.67 -> 22.89Improved
add trajectory optimization to the diffusion planner (ablation)M2Diffuser · Test Set One, goal-reachingsuccess rate (%): 25.49 -> 30.49Improved
add trajectory optimization to the diffusion planner (ablation)M2Diffuser · Test Set Two, graspingsuccess rate (%): 9.25 -> 14.33Improved
add trajectory optimization to the diffusion planner (ablation)M2Diffuser · Test Set Two, placementsuccess rate (%): 5.70 -> 12.25Improved
add trajectory optimization to the diffusion planner (ablation)M2Diffuser · Test Set Two, goal-reachingsuccess rate (%): 9.19 -> 12.61Improved
add trajectory optimization to the diffusion planner (ablation)M2Diffuser · Test Set One, graspingcollision rate (%): 34.27 -> 20.29Improved
add trajectory optimization to the diffusion planner (ablation)M2Diffuser · Test Set One, placementcollision rate (%): 42.44 -> 24.78Improved
add trajectory optimization to the diffusion planner (ablation)M2Diffuser · Test Set Two, graspingcollision rate (%): 53.13 -> 36.42Improved
add trajectory optimization (increases solving time) (ablation)M2Diffuser · Test Set One, graspingsolving time (s): 0.47 -> 4.74Hurt
add learned diffusion prior to guided trajectory optimization (ablation)M2Diffuser · Goal-reaching (100 tasks)success rate (%): 0.00 -> 51.00Improved
add learned diffusion prior to guided trajectory optimization (ablation)M2Diffuser · Goal-reaching (100 tasks)collision depth (m): 6.65 -> 4.79Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy