Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Advancing Human-Machine Teaming: Concepts, Challenges, and Applications

Dian Chen, Han Jun Yoon, Zelin Wan, Nithin Alluru, Sang Won Lee, Richard He, Terrence J. Moore, Frederica F. Nelson, Sunghyun Yoon, Hyuk Lim, Dan Dongseong Kim, Jin-Hee Cho

TL;DR

This survey advances Human-Machine Teaming (HMT) by offering a unified taxonomy, a cross-disciplinary evaluation framework, and an empirical synthesis of performance drivers across training, autonomy, trust, and shared cognition. It integrates three theoretical lenses—Human-in-the-Loop Reinforcement Learning, Instance-Based Learning Theory, and Interdependence Theory—while emphasizing trustworthy design, ethics, and multi-domain applicability. The work also foregrounds evaluation methodologies, testbeds, and datasets, highlighting gaps in real-world validation and standardized benchmarking. Together, these contributions lay a foundation for resilient, ethical, and scalable HMT systems with practical impact across defense, healthcare, robotics, and cyber domains.

Abstract

Human-Machine Teaming (HMT) is revolutionizing collaboration across domains such as defense, healthcare, and autonomous systems by integrating AI-driven decision-making, trust calibration, and adaptive teaming. This survey presents a comprehensive taxonomy of HMT, analyzing theoretical models, including reinforcement learning, instance-based learning, and interdependence theory, alongside interdisciplinary methodologies. Unlike prior reviews, we examine team cognition, ethical AI, multi-modal interactions, and real-world evaluation frameworks. Key challenges include explainability, role allocation, and scalable benchmarking. We propose future research in cross-domain adaptation, trust-aware AI, and standardized testbeds. By bridging computational and social sciences, this work lays a foundation for resilient, ethical, and scalable HMT systems.

Advancing Human-Machine Teaming: Concepts, Challenges, and Applications

TL;DR

This survey advances Human-Machine Teaming (HMT) by offering a unified taxonomy, a cross-disciplinary evaluation framework, and an empirical synthesis of performance drivers across training, autonomy, trust, and shared cognition. It integrates three theoretical lenses—Human-in-the-Loop Reinforcement Learning, Instance-Based Learning Theory, and Interdependence Theory—while emphasizing trustworthy design, ethics, and multi-domain applicability. The work also foregrounds evaluation methodologies, testbeds, and datasets, highlighting gaps in real-world validation and standardized benchmarking. Together, these contributions lay a foundation for resilient, ethical, and scalable HMT systems with practical impact across defense, healthcare, robotics, and cyber domains.

Abstract

Human-Machine Teaming (HMT) is revolutionizing collaboration across domains such as defense, healthcare, and autonomous systems by integrating AI-driven decision-making, trust calibration, and adaptive teaming. This survey presents a comprehensive taxonomy of HMT, analyzing theoretical models, including reinforcement learning, instance-based learning, and interdependence theory, alongside interdisciplinary methodologies. Unlike prior reviews, we examine team cognition, ethical AI, multi-modal interactions, and real-world evaluation frameworks. Key challenges include explainability, role allocation, and scalable benchmarking. We propose future research in cross-domain adaptation, trust-aware AI, and standardized testbeds. By bridging computational and social sciences, this work lays a foundation for resilient, ethical, and scalable HMT systems.

Paper Structure

This paper contains 58 sections, 10 figures, 11 tables.

Table of Contents

  1. Introduction
  2. Comparison with Existing Surveys
  3. Key Contributions
  4. Taxonomies of HMT Systems
  5. Related Concepts and Key Factors in HMT
  6. Key Components of HMT Systems
  7. Architecture of an HMT System
  8. Key Components of Trustworthy HMT Systems
  9. Empirical Studies to Promote Team Performance
  10. Team Training
  11. Team Autonomy
  12. Trust & Decision-Making
  13. Shared Mental Model (SMM)
  14. Team Situation Awareness
  15. Synergistic Human-AI Collaboration
  16. ...and 43 more sections

Figures (10)

  • Figure 1: Structure of this review paper.
  • Figure 2: Hierarchical diagram illustrating relationships and dependencies among HMT-related concepts.
  • Figure 3: Conceptual relationships of the key factors influencing the performance of HMT systems.
  • Figure 4: Architecture of a human-machine teaming system based on its core components.
  • Figure 5: Attributes of a trustworthy HMT system based on the STRAM framework.
  • ...and 5 more figures