Interaction Paradigms: from Human-Human Teaming to Human-Autonomy Teaming

Tokadli, Guliz; Dorneich, Michael C.

doi:10.1109/dasc43569.2019.9081665

Cited by 14 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Human: The human component of HAT includes workers with expertise, knowledge, and skills that are essential for achieving the team's goals. 41 Human workers are responsible for tasks that require judgment, decision-making, creativity, and interpersonal communication.…”

Section: Key Components and Aspects Of Human-autonomy Teamingmentioning

confidence: 99%

Joint human and autonomy teaming for defense: status, challenges, and perspectives

El Alami,

Nwosu,

Rawat

2023

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V

View full text Add to dashboard Cite

Human and Autonomy Teaming (HAT) involves humans, artificial intelligence and machine learning (AI/ML), and autonomous systems (AS) working together to enhance performance and efficiency across a variety of fields. The purpose of this paper is to outline the current status, challenges, and perspectives related to HAT in the defense applications, such as multi-domain operations (MDOs). This paper emphasizes that, although ASs have numerous benefits, humans, and machines need to work together to ensure effective communication and coordination. Furthermore, this paper addresses the issues of situation awareness, HAT bias, security, privacy, confidentiality, trust, transparency, and explainability as they relate to joint HAT in MDOs. Finally, this paper explores the potential of perspectives to overcome these challenges and enhance collaboration between humans, AI/ML, and AS in the context of defense.

show abstract

Section: Key Components and Aspects Of Human-autonomy Teamingmentioning

confidence: 99%

Joint human and autonomy teaming for defense: status, challenges, and perspectives

El Alami,

Nwosu,

Rawat

2023

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V

View full text Add to dashboard Cite

show abstract

“…As the capability and intelligence of autonomy increases and the proliferation of those autonomous systems expands in both civilian and military domains, the need to reformulate the interaction between humans and autonomy from that of user-to-tool to that of teammate-to-teammate, and focus on enhancing teaming (e.g., states, processes, individualization), will be increasingly critical [1]. Autonomous systems that approach and surpass parity with human counterparts will naturally be involved in an increasing proportion of taskwork and teamwork, motivating a decrease in the granularity of human involvement and oversight of their behavior, as well as a need to maintain shared awareness with and build trust in those autonomous systems to behave in accordance with human intent [2].…”

Section: Introduction 11 the Need For Explainable Autonomy And Human-...mentioning

confidence: 99%

Multi-agent playbook for human-robot teaming

Handelman

Holmes

Badger

et al. 2023

Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications V

View full text Add to dashboard Cite

Effective human-robot teaming requires human and robot teammates to share a common understanding of the goals of their collaboration. Ideally, a complex task can be broken into smaller components to be performed by team members with defined roles, and the plan of action and assignment of roles can be changed on the fly to accommodate unanticipated situations. In this paper we describe research on adaptive human-robot teaming that uses a playbook approach to team behavior to bootstrap multi-agent collaboration. The goal is to leverage known good strategies for accomplishing tasks, such as from training and operating manuals, to enable humans and robots to "be on the same page" and work from a common knowledge base. Simultaneous and sequential actions are specified using hierarchical text-based plans and executed as behavior trees using finite state machines. We describe a real-time implementation that supports sharing of task status updates through distributed message passing. Tasks related to human-robot teaming for exploration and reconnaissance are explored with teams comprising humans wearing augmented reality headsets and quadruped robots. It is anticipated that shared task knowledge provided by multi-agent playbooks will enable humans and robots to track and predict teammate behavior and promote team transparency, accountability and trust.

show abstract

“…In addition to communication, individuals in high-performing human teams also benefit from the theory of mind (Frith & Frith, 2005) and making strategic decisions by recursively reasoning about the actions (strategies) of other human members (Goodie et al, 2012). Such hierarchical rationalization alongside with communication facilitate meaningful cooperation in human teams (Tokadli & Dorneich, 2019). Similarly, collaborative Multi-agent Reinforcement Learning (MARL) relies on meaningful cooperation among interacting agents in a common environment (Oliehoek & Amato, 2016).…”

Section: Introductionmentioning

confidence: 99%

Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming

Konan¹,

Seraj²,

Gombolay³

2022

Preprint

View full text Add to dashboard Cite

Information sharing is key in building team cognition and enables coordination and cooperation. High-performing human teams also benefit from acting strategically with hierarchical levels of iterated communication and rationalizability, meaning a human agent can reason about the actions of their teammates in their decisionmaking. Yet, the majority of prior work in Multi-Agent Reinforcement Learning (MARL) does not support iterated rationalizability and only encourage inter-agent communication, resulting in a suboptimal equilibrium cooperation strategy. In this work, we show that reformulating an agent's policy to be conditional on the policies of its neighboring teammates inherently maximizes Mutual Information (MI) lower-bound when optimizing under Policy Gradient (PG). Building on the idea of decision-making under bounded rationality and cognitive hierarchy theory, we show that our modified PG approach not only maximizes local agent rewards but also implicitly reasons about MI between agents without the need for any explicit ad-hoc regularization terms. Our approach, InfoPG, outperforms baselines in learning emergent collaborative behaviors and sets the state-of-the-art in decentralized cooperative MARL tasks. Our experiments validate the utility of InfoPG by achieving higher sample efficiency and significantly larger cumulative reward in several complex cooperative multi-agent domains.

show abstract

Interaction Paradigms: from Human-Human Teaming to Human-Autonomy Teaming

Cited by 14 publications

References 35 publications

Joint human and autonomy teaming for defense: status, challenges, and perspectives

Joint human and autonomy teaming for defense: status, challenges, and perspectives

Multi-agent playbook for human-robot teaming

Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming

Contact Info

Product

Resources

About