AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion

Chiyu “Max” Jiang, Andre Cornman, Cheolho Park, Benjamin Sapp, Yin Zhou, Dragomir Anguelov

CVPR 2023 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 156 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
replace Wayformer's prediction head with the MotionDiffuser diffusion headWayformer backbone · WOMD Interactive validationminSADE: 0.99 -> 0.86Improved
replace Wayformer's prediction head with the MotionDiffuser diffusion headWayformer backbone · WOMD Interactive validationmAP: 0.16 -> 0.19Improved
use MotionDiffuser instead of JFPWOMD Interactive test · WOMD Interactive testminSADE: 0.88 -> 0.86Improved
use MotionDiffuser instead of JFPWOMD Interactive test · WOMD Interactive testmAP: 0.21 -> 0.20Hurt
apply attractor guidance to target the ground-truth final pointMotionDiffuser · WOMD Interactive validation, attractor constraintSR2m: 0.059 -> 0.952Improved
apply attractor guidance rather than post-sampling trajectory optimizationMotionDiffuser · WOMD Interactive validation, attractor constraintminSADE: 4.563 -> 0.533Improved
apply repeller guidance between modeled agentsMotionDiffuser · WOMD Interactive validation, repeller constraintOverlap: 0.059 -> 0.008Improved
add PCA-compressed trajectory representation (ablation)MotionDiffuser · WOMD Interactive validationminSADE: 1.03 -> 0.88Improved
use a Transformer denoiser instead of a simple MLP (ablation)MotionDiffuser · WOMD Interactive validationminSADE: 0.93 -> 0.88Improved
add self-attention between agents' noisy future trajectories (ablation)MotionDiffuser · WOMD Interactive validationminSADE: 0.91 -> 0.88Improved
add score thresholding to constraint guidance (ablation)MotionDiffuser attractor sampling · WOMD Interactive validation, attractor constraintminSFDE: 0.627 -> 0.007Improved

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