A Bayesian Reasoning Framework for Robotic Systems in Autonomous Casualty Triage

2026-04-23

AI Summary

This work addresses the challenge of reliable casualty triage by autonomous robots in mass-casualty incidents, where perception data are often incomplete and noisy. The authors propose a Bayesian inference framework that integrates multimodal visual perception with expert-derived rules, uniquely embedding an expert-guided Bayesian network deeply within a multisource visual system to enable probabilistic assessment of casualty status. This approach ensures robust decision-making even under conditions of perceptual ambiguity or conflicting evidence. Evaluated in the DARPA Triage Challenge, the method nearly triples physiological assessment accuracy—from 15% to 42% and from 19% to 46% across test scenarios—while increasing overall triage accuracy from 14% to 53% and dramatically improving diagnostic coverage from 31% to 95%.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Reasoning under Uncertainty: Probabilistic Inference
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Autonomous robots deployed in mass casualty incidents (MCI) face the challenge of making critical decisions based on incomplete and noisy perceptual data. We present an autonomous robotic system for casualty assessment that fuses outputs from multiple vision-based algorithms, estimating signs of severe hemorrhage, visible trauma, or physical alertness, into a coherent triage assessment. At the core of our system is a Bayesian network, constructed from expert-defined rules, which enables probabilistic reasoning about a casualty's condition even with missing or conflicting sensory inputs. The system, evaluated during the DARPA Triage Challenge (DTC) in realistic MCI scenarios involving 11 and 9 casualties, demonstrated a nearly three-fold improvement in physiological assessment accuracy (from 15\% to 42\% and 19\% to 46\%) compared to a vision-only baseline. More importantly, overall triage accuracy increased from 14\% to 53\%, while the diagnostic coverage of the system expanded from 31\% to 95\% of cases. These results demonstrate that integrating expert-guided probabilistic reasoning with advanced vision-based sensing can significantly enhance the reliability and decision-making capabilities of autonomous systems in critical real-world applications.

Problem

• autonomous casualty triage
• mass casualty incidents
• incomplete perceptual data
• triage accuracy
• robotic decision-making

Innovation

• Bayesian reasoning
• autonomous triage
• vision-based sensing
• probabilistic fusion
• mass casualty incident