Autonomous Search-and-Triage Robots for the DARPA Triage Challenge
I’m leading Penn’s team (PRONTO - Penn RObotics Non-contact Triage and Observation) for the DARPA Triage Challenge, the latest in the DARPA robotics challenge series. We’re developing a heterogeneous fleet of robots, including both ground and aerial systems, to assist first responders in locating and triaging casualties during mass casualty incidents. Our team consists of faculty from GRASP (Eaton, Taylor, Daniilidis) and Penn Trauma (Cannon, Qasim, Yelon) with over 20 student researchers.
We successfully completed the first two years of competition, and, based on our performance, were selected by DARPA to continue to the finals in November 2026. Our approach combines fundamental robotics (multi-robot navigation, coordination, and autonomy) with machine learning (multimodal visual-language models, deep neural networks) for victim perception, vital sign monitoring, and injury assessment (Hughes et al., 2025).
Our falcon quadrotor surveys the scene while jackal ground robots visit each casualty to assess their injuries and vital signs in this simulated battlefield scene
One of our jackal ground robots navigates to a casualty during Competition 2.
Our work, along with those of the other teams competing, is showcased in this highlights reel from Competition 2, held in Perry, GA in October 2025.
During Competion 1's simulated convoy attack, our Falcon quadrotor locates casualties while two jackal ground robots assess each casualty's injuries and vital signs.
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.
@misc{Hughes2025MultiRobotTriage,title={A Multi-Robot Platform for Robotic Triage Combining Onboard Sensing and Foundation Models},author={Hughes, Jason and Hussing, Marcel and Zhang, Edward and Kannapiran, Shenbagaraj and Caswell, Joshua and Chaney, Kenneth and Deng, Ruichen and Feehery, Michaela and Kratimenos, Agelos and Li, Yi Fan and Major, Britny and Sanchez, Ethan and Shrote, Sumukh and Wang, Youkang and Wang, Jeremy and Zein, Daudi and Zhang, Luying and Zhang, Ruijun and Zhou, Alex and Zhouga, Tenzi and Cannon, Jeremy and Qasim, Zaffir and Yelon, Jay and Cladera, Fernando and Daniilidis, Kostas and Taylor, Camillo J. and Eaton, Eric},year={2025},eprint={2512.08754},archiveprefix={arXiv},primaryclass={cs.RO},url={https://arxiv.org/abs/2512.08754},}
I’m leading Penn’s team (PRONTO - Penn RObotics Non-contact Triage and Observation) for the DARPA Triage Challenge, the latest in the DARPA robotics challenge series. We’re developing a heterogeneous fleet of robots, including both ground and aerial systems, to assist first responders in locating and triaging casualties during mass casualty incidents. Our team consists of faculty from GRASP (Eaton, Taylor, Daniilidis) and Penn Trauma (Cannon, Qasim, Yelon) with over 20 student researchers.
