HumanDiffusion: A Vision-Based Diffusion Trajectory Planner with Human-Conditioned Goals for Search and Rescue UAV

TL;DR

HumanDiffusion introduces a novel image-based diffusion planning method enabling UAVs to generate human-aware navigation trajectories directly from RGB images, improving safety and efficiency in emergency search and rescue operations.

Contribution

The paper presents HumanDiffusion, a lightweight diffusion-based trajectory planner that integrates human detection with direct RGB image conditioning for UAV navigation in rescue scenarios.

Findings

Achieves 0.02 pixel-space trajectory reconstruction error.

Demonstrates 80% success rate in real-world rescue tasks.

Operates without prior maps or heavy computation.

Abstract

Reliable human--robot collaboration in emergency scenarios requires autonomous systems that can detect humans, infer navigation goals, and operate safely in dynamic environments. This paper presents HumanDiffusion, a lightweight image-conditioned diffusion planner that generates human-aware navigation trajectories directly from RGB imagery. The system combines YOLO-11 based human detection with diffusion-driven trajectory generation, enabling a quadrotor to approach a target person and deliver medical assistance without relying on prior maps or computationally intensive planning pipelines. Trajectories are predicted in pixel space, ensuring smooth motion and a consistent safety margin around humans. We evaluate HumanDiffusion in simulation and real-world indoor mock-disaster scenarios. On a 300-sample test set, the model achieves a mean squared error of 0.02 in pixel-space trajectory reconstruction. Real-world experiments demonstrate an overall mission success rate of 80% across accident-response and search-and-locate tasks with partial occlusions. These results indicate that human-conditioned diffusion planning offers a practical and robust solution for human-aware UAV navigation in time-critical assistance settings.