Primary Triage

Systems Competition

During primary triage in the field, casualties are assessed to determine priorities for treatment on scene and transport of patients to hospital.

The objective of the Systems Competition is to detect and identify physiological signatures of injury derived from data captured by stand-off sensors onboard autonomous systems. This will enable early prioritization of casualties in primary triage, allowing medical care professionals to quickly focus on the most urgent casualties.

Teams will develop algorithms that detect those signatures in real-time from stand-off sensor data to provide decision support appropriate for austere and complex pre-hospital settings. Teams will use their stand-off sensors, robotic mobility platforms (e.g., UAVs, UGVs), and algorithms to autonomously process sensor data and provide real-time casualty identification and injury assessment. Of particular interest are signatures of acutely life-threatening conditions that medics are trained and equipped to treat during primary triage, such as hemorrhage and airway injuries.

Primary triage assesment illustration

Technical Challenge Elements:

Degraded Sensing Icon
Degraded Sensing

The courses are expected to include elements that range from constrained passages to large fields, lighted areas to complete darkness, and wet to dusty conditions. Sensors will need to have the dynamic range to operate reliably in these environments. Dust, fog, mist, smoke, talking, flashing light, hot spots, and gunshot and explosion sounds are within scope of this challenge element. Extreme temperatures, fire, tremors, and hazardous materials are not expected to be within scope.

Obscuring Obstacles Icon
Obscuring Obstacles

Casualties may be fully visible to partially obscured to completely obscured, such as buried under a shallow layer of rubble. Sensor modalities capable of penetrating rubble may have an advantage in such situations. Casualties may also be grouped with limbs overlapping, or may be interacting with live responders.

Terrain Obstacles Icon
Terrain Obstacles:

The competition scenarios will be held in realistic environments that may include natural or human-made materials; structured or unstructured clutter; and intact or collapsed structures and debris. Robotic mobility is not the focus of this challenge and it is expected that widely available outdoor robotic platforms will be capable of navigating the competition environments. In some cases, more robust platforms may benefit from more direct navigation paths or closer approach paths to casualties.

Dynamic Obstacles Icon
Dynamic Obstacles

Live responders, ambulatory wounded, or other physical changes to the environment may be included to test the agility of the system autonomy to identify and assess casualties.

Dynamic Casualties Icon
Dynamic Casualties

Some treatable injuries may rapidly become fatal, and delays in finding and assessing casualties may result in missing the window for effective LSI. While competitors are not expected to re-evaluate casualties for changes in status, casualties who are not evaluated within an appropriate timescale may have a change in status (for example, progression of untreated hemorrhage or airway injury).

Endurance Limits Icon
Endurance Limits:

It is expected that individual scenarios will run <30 minutes. Teams may be permitted to replace batteries during their run, but teams should consider the implications of returning to the original launch location and redeploying their systems.

Real-World systems will use stand-off sensors on platforms to locate and triage casualties in the field

Systems Competition

*Total system should fits in a single vehicle

Skills Required

Autonomous systems, sensors, UI development, machine learning, medical knowledge

Scoring Criteria

  • Percent of casualties identified
  • Accuracy in reporting casualty locations 
  • Accuracy of casualty injury classification  
  • Time to complete casualty assessments 
  • Identification of urgent casualties before the opportunity to address life-saving interventions (LSIs) would have closed 

Team Qualification

For more information, please refer to team qualifications guide, the kick off slides and the broad agency announcement (BAA). Qualification is for self-funded teams only.

System Competition Teams

AIR TAGS: Automated Image and Radar-based Triage, Assessment, and Geolocation System (DARPA-funded)

  • Arete
  • University of Colorado, Boulder
  • Critical Innovations

APAT: AI Powered Autonomous Triage

  • Mmh Labs, Purdue University

Chiron (DARPA-funded)

  • Carnegie Mellon University
  • University of Pittsburgh

Coordinated Robotics

  • Coordinated Robotics
  • California State University Channel Islands

DART: Drone Assisted Rapid Triage (DARPA-funded)

  • Battelle Memorial Institute

Engineering Dynamics and RIIS

  • Engineering Dynamics


  • Elegant Mathematics Ltd, Germany
  • Elegant Mathematics LLC, USA

POINTER: Point of Injury Navigation, Triage, and Emergency Response (DARPA-funded)

  • Charles River Analytics
  • University of Massachusetts Medical School
  • University of California-Irvine


  • PRISM Intelligence Inc

PRONTO: Penn RObotic Non-contact Triage and Observation (DARPA-funded)

  • University of Pennsylvania

RAPID: Reliable Assessment of People in Disasters (DARPA-funded)

  • Raytheon BBN
  • Valkyries Austere Medical Services
  • Skydio

RESCUE: Reliable Evaluation and Sensing of Casualties in Uncertain Environments

  • Ichor Autonomy Pty Ltd., Australia

RoboScout (DARPA-funded)

  • University of Maryland College Park
  • University of Maryland UAS Research and Operations Center
  • University of Maryland School of Medicine

TTT: TAK Triage Technologies

  • Individuals

UAS-DTU: Unmanned Aerial Systems Delhi Technological University

  • Delhi Technological University, India