Automating Convoy Training Assessment to Improve Soldier Performance

Abstract

Monitoring teams of decision-makers in complex military environments requires effective tracking of individual Soldier and team performance. An untapped source of timely and diagnostic performance information lies in ongoing communications among Soldiers operating as a team. With the right analyses the communication data can be connected to both the team's and each individual's performance, abilities and knowledge. The DARCAAT program developed and tested a toolset for automating team assessment and near real-time alarms. The toolset uses Automated Speech Recognition and Statistical Natural Language-based techniques for embedding automatic, continuous, and cumulative analysis of team communication in training and operational environments. Based on the toolset, applications were developed that apply the metrics and models to support After Action Reviews (AARs) and real-time alarms.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2008
Accession Number
ADA506208

Entities

People

  • Joe Psotka
  • Mark Rosenstein
  • Noelle LaVoie
  • Peter Foltz
  • Ralph Chatham
  • Rob Oberbreckling

Tags

Communities of Interest

  • Autonomy
  • C4I
  • Engineered Resilient Systems
  • Human Systems

DTIC Thesaurus Topics

  • Automated Speech Recognition
  • Cognitive Science
  • Command And Control
  • Computational Linguistics
  • Computational Science
  • Computer Languages
  • Improvised Explosive Devices
  • Language
  • Linguistics
  • Machine Learning
  • Markov Models
  • Natural Language Processing
  • Natural Languages
  • Network Science
  • Recognition
  • Supervised Machine Learning
  • Training

Readers

  • Database Systems and Applications
  • Military Training and Readiness Simulation
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML