A Multi-Robot Platform for Robotic Triage Combining Onboard Sensing and Foundation Models

2025-12-09

AI Summary

To address the high risk and low efficiency of manual triage in mass casualty incidents (MCIs), this paper proposes an aerial-ground collaborative heterogeneous robotic system for remote, automated primary triage. The system integrates multi-rotor unmanned aerial vehicles (UAVs) for wide-area rapid search and overhead localization, and ground robots equipped with multimodal sensors for precise vital sign acquisition and injury localization. Innovatively combining multi-robot coordinated control with vision foundation models, it achieves, for the first time, an end-to-end closed-loop triage pipeline—including casualty localization, physiological monitoring, injury severity classification, and consciousness assessment. Onboard perception, cross-platform data fusion, and task-level coordination significantly improve response speed and assessment accuracy. Validated in the DARPA Triage Challenge, the system demonstrates robustness in complex environments, effectively reducing first-responder exposure risk and enhancing casualty survival rates.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Computer Vision: Multi-modal Vision

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

This report presents a heterogeneous robotic system designed for remote primary triage in mass-casualty incidents (MCIs). The system employs a coordinated air-ground team of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) to locate victims, assess their injuries, and prioritize medical assistance without risking the lives of first responders. The UAV identify and provide overhead views of casualties, while UGVs equipped with specialized sensors measure vital signs and detect and localize physical injuries. Unlike previous work that focused on exploration or limited medical evaluation, this system addresses the complete triage process: victim localization, vital sign measurement, injury severity classification, mental status assessment, and data consolidation for first responders. Developed as part of the DARPA Triage Challenge, this approach demonstrates how multi-robot systems can augment human capabilities in disaster response scenarios to maximize lives saved.

Problem

• Develops a multi-robot system for remote triage in mass-casualty incidents.
• Uses UAVs and UGVs to locate victims and assess injuries autonomously.
• Addresses the complete triage process to prioritize medical assistance safely.

Innovation

• Multi-robot air-ground team for remote triage
• Onboard sensors and foundation models assess injuries
• Complete automated triage from localization to data consolidation