# EmbodiedDiffusion: End-to-End Traversability-Guided Visual Diffusion for Heterogeneous Robot Navigation

arXiv: https://arxiv.org/abs/2512.02851 · HTML: https://mlsanity.com/paper/2512.02851/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- First posted on arXiv 2 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Built on by (most cited first, 4 of 4)

- [HumanDiffusion: A Vision-Based Diffusion Trajectory Planner with Human-Conditioned Goals for Search and Rescue UAV](https://mlsanity.com/paper/2601.14973/) (2026)
- [DiffusionCinema: Text-to-Aerial Cinematography](https://mlsanity.com/paper/2601.17412/) (2026)
- [Guided Diffusion with Distilled Vision-Language Reliability for Aerial Navigation](https://mlsanity.com/paper/2606.13883/) (2026)
- [CloudDiffusion: Diffusion-Based Scene Completion in the Point Cloud Domain](https://mlsanity.com/paper/2606.16048/) (2026)

## Abstract (arXiv)

Visual traversability estimation is central to autonomous navigation, yet most approaches either rely on prompt-driven Vision-Language Model (VLM) or decouple traversability from trajectory planning, requiring separate planners with heavy mapping, manual tuning, and extended deployment time. We propose EmbodiedDiffusion, a diffusion-based framework that simultaneously predicts traversability maps and generates feasible trajectories from RGB images using planner-free synthetic supervision and embodiment conditioning for cross-platform transfer. The framework distills category-level traversability semantics from a VLM teacher into a lightweight student model during training, enabling prompt-free, real-time inference at deployment. A modular FiLM-based conditioning mechanism isolates embodiment-specific reasoning into a compact trainable subset of the network, allowing rapid adaptation to new robot platforms without retraining the visual backbone or the trajectory diffusion model. Across indoor environments with quadruped and aerial robots, EmbodiedDiffusion achieves 80-100% navigation success in the full-data regime with real-time inference (90 ms) and adapts to new platforms using only 10 min of visual data collection, demonstrating scalable, unified traversability reasoning and trajectory generation for heterogeneous robots.