Diffusion Models for Embodied Perception and World Modeling: A Survey from a Humanoid Robotics Perspective

Humanoid intelligence requires agents to perceive uncertain environments, infer structured representations from multimodal sensory observations, and predict future world evolution before acting. Otherwise, recent advances in diffusion models have extended their role far beyond image synthesis, enabling probabilistic perception, spatial scene understanding, and predictive world modeling for embodied AI. By modeling complex data distributions through conditional generation, diffusion models naturally address uncertainty, partial observability, and multimodal future prediction, making them particularly suitable for embodied perception and predictive imagination. This survey provides a comprehensive review of diffusion models for embodied perception and world modeling. We first trace the evolution of humanoid robotics and introduce the diffusion formulations underlying the surveyed methods, and then propose a unified taxonomy that organizes existing methods from probabilistic perception to predictive imagination. We comprehensively review diffusion-based approaches for human perception, embodied self-perception, and environment understanding. For world modeling, we analyze the advantages of diffusion model for observation space prediction, compact learned latent spaces, and conditioning on explicit robot actions or latent actions inferred from video. By unifying recent advances in perception and predictive world modeling, this survey highlights diffusion models as a general probabilistic framework for embodied intelligence and outlines promising directions toward more capable and reliable embodied AI systems.

Authors

Publication Details

Journal
Preprints.org
Published
2026-11-17
DOI
https://doi.org/10.20944/preprints202611.1677.v1
Primary Topic
Reinforcement Learning in Robotics
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Diffusion Models for Embodied Perception and World Modeling: A Survey from a Humanoid Robotics Perspective

Dong In Kim, Dusit Niyato, Nguyen Cong Luong, Hung-Le Hoang et al.
1 links
Preprints.org
Reinforcement Learning in Robotics
preprint

Diffusion Models for Embodied Perception and World Modeling: A Survey from a Humanoid Robotics Perspective

Dong In Kim, Dusit Niyato, Nguyen Cong Luong, Hung-Le Hoang, Minh-Duong Nguyen
preprint en

Abstract

Humanoid intelligence requires agents to perceive uncertain environments, infer structured representations from multimodal sensory observations, and predict future world evolution before acting. Otherwise, recent advances in diffusion models have extended their role far beyond image synthesis, enabling probabilistic perception, spatial scene understanding, and predictive world modeling for embodied AI. By modeling complex data distributions through conditional generation, diffusion models naturally address uncertainty, partial observability, and multimodal future prediction, making them particularly suitable for embodied perception and predictive imagination. This survey provides a comprehensive review of diffusion models for embodied perception and world modeling. We first trace the evolution of humanoid robotics and introduce the diffusion formulations underlying the surveyed methods, and then propose a unified taxonomy that organizes existing methods from probabilistic perception to predictive imagination. We comprehensively review diffusion-based approaches for human perception, embodied self-perception, and environment understanding. For world modeling, we analyze the advantages of diffusion model for observation space prediction, compact learned latent spaces, and conditioning on explicit robot actions or latent actions inferred from video. By unifying recent advances in perception and predictive world modeling, this survey highlights diffusion models as a general probabilistic framework for embodied intelligence and outlines promising directions toward more capable and reliable embodied AI systems.

Preprints.org
Reinforcement Learning in Robotics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon