A Virtual Environment with Multi-Robot Navigation, Analytics, and Decision Support for Critical Incident Investigation

TL;DR

This paper presents a virtual environment designed for multi-robot navigation, analytics, and decision support to assist in critical incident investigations involving hazardous substances, aiming to improve AI-assisted assessment and response.

Contribution

It introduces realistic CBRNE scenario models and initial AI tools to aid investigators, supporting simulation-based development and evaluation of decision-making systems.

Findings

Developed realistic CBRNE scenario models

Implemented initial AI decision support tools

Facilitated simulation-based evaluation of investigation strategies

Abstract

Accidents and attacks that involve chemical, biological, radiological/nuclear or explosive (CBRNE) substances are rare, but can be of high consequence. Since the investigation of such events is not anybody's routine work, a range of AI techniques can reduce investigators' cognitive load and support decision-making, including: planning the assessment of the scene; ongoing evaluation and updating of risks; control of autonomous vehicles for collecting images and sensor data; reviewing images/videos for items of interest; identification of anomalies; and retrieval of relevant documentation. Because of the rare and high-risk nature of these events, realistic simulations can support the development and evaluation of AI-based tools. We have developed realistic models of CBRNE scenarios and implemented an initial set of tools.