A Bayesian Reasoning Framework for Robotic Systems in Autonomous Casualty Triage
Szymon Rusiecki, Cecilia Morales, Pia Störy, Kimberly Elenberg, Leonard Weiss, Artur Dubrawski
AI summary
Problem
Autonomous robots in mass casualty incidents struggle with noisy, incomplete, and occluded sensor data, causing isolated perception algorithms to fail at reliable casualty assessment.
Approach
The system fuses multiple vision-based sensor outputs into a unified probabilistic estimate using an expert-elicited Bayesian network, enabling robust reasoning under uncertainty and missing data.
Key results
- Overall triage accuracy increased from 14% to 53%
- Diagnostic coverage expanded from 31% to 95%
- Physiological assessment accuracy improved nearly three-fold
- Real-time inference achieved in under 1 millisecond with <100 MB memory
Why it matters
Provides a scalable, transparent decision-support framework for deploying autonomous robots in high-stakes disaster response where data is unreliable and time is critical.
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 real- istic 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.