Acousticdiffusion guides rescue robots to human callers using sound
AcousticDiffusion: Semantically Conditioned Audio-Guided Diffusion Policy for Search-and-Rescue Assistance
Robotics
Summary
Finding and navigating to people calling for help is challenging for rescue robots, especially when vision is limited. The authors created AcousticDiffusion, a system that listens for human speech and distress signals to guide robots toward callers using sounds. By combining audio recognition, sound direction, and a smart planning model, the system helps robots move closer to people needing rescue. It worked better than classic methods in tests, reducing the distance to callers and ignoring irrelevant noise.
What this means in practice
- •For robotics engineers: Improve robot navigation in search-and-rescue missions using audio to find people calling for help when vision is blocked.
- •For emergency response teams: Deploy robots that can better locate distressed humans by following sounds even in noisy or visually obscured environments.
Authors
Iana Zhura, Didar Seyidov, Dmitrii Plotnikov, Hajira Amjad, Miguel Altamirano Cabrera, Dzmitry Tsetserukou
Abstract
Navigating toward human callers is an important capability for rescue robots operating where visual contact is degraded or occluded. We present AcousticDiffusion, a semantically conditioned, audio-guided diffusion policy for human-directed navigation. A frozen pretrained audio recognizer processes 10.24 s windows, with speech gating and distress-aware prioritization converting recognition outputs into source-level navigation roles. Microphone-array direction-of-arrival measurements are recursively integrated into a robot-centric Bayesian bird's-eye-view belief field. Ego-motion compensation aligns successive observations, progressively constraining source position while preserving bearing-induced range uncertainty. The semantic belief, recent acoustic observations, audio features, and robot state condition a diffusion model that generates waypoint trajectories. On a synthetic-navigation validation set using recorded audio, AcousticDiffusion achieves a mean end-point bearing error of 11.20 degrees, with 91.78% of trajectories aligned within 30 degrees of the caller. Distractor rejection ranges from 89.20% to 98.99%, and the policy favors a HELP-designated caller over a competing speaker in 91.07% of windows. Deployed online on a ZSL-1 quadruped without additional retraining, it achieves a mean bearing error of 64.9 degrees, compared with 98.2 degrees for A* and 90.4 degrees for RRT, with a mean planner compute time of 6.07 ms. Despite imperfect acoustic localization, the reported mean final source distance is reduced from 3.96 m for the classical planners using ODAS-derived (Open embedded Audition System) guidance to 2.48 m, a 37.4% improvement. These results demonstrate the framework's ability to translate uncertain acoustic observations into closer approaches to human callers.