Human-Swarm-Teaming Transparency and Trust Architecture

Hepworth, Adam J.; Baxter, Daniel P.; Hussein, Aya; Yaxley, Kate J.; Debie, Essam; Abbass, Hussein A.

doi:10.1109/jas.2020.1003545

Cited by 28 publications

(25 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We posit that the services described in this architecture provide the fundamental elements required to share critical semantic information between agents. We assert that an ontology will help to deliver transparency through higher-level intent sharing and understanding for contexts and situations in HST missions (semantic information sharing), as described by Hepworth et al ( 2021) [11]. The key idea here is that a knowledge-grounded approach grounds the concepts with relations, providing context for an AI to understand and reason about the environment.…”

Section: Designing An Ontology For Generalised Multi-agent Teamingmentioning

confidence: 97%

Onto4MAT: A Swarm Shepherding Ontology for Generalised Multi-Agent Teaming

Hepworth¹,

Baxter²,

Abbass³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Research in multi-agent teaming has increased substantially over recent years, with knowledge-based systems to support teaming processes typically focused on delivering functional (communicative) solutions for a team to act meaningfully in response to direction. Enabling humans to effectively interact and team with a swarm of autonomous cognitive agents is an open research challenge in Human-Swarm Teaming research, partially due to the focus on developing the enabling architectures to support these systems. Typically, bi-directional transparency and shared semantic understanding between agents has not prioritised a designed mechanism in Human-Swarm Teaming, potentially limiting how a human and a swarm team can share understanding and information-data through concepts and contexts-to achieve a goal. To address this, we provide a formal knowledge representation design that enables the swarm Artificial Intelligence to reason about its environment and system, ultimately achieving a shared goal. We propose the Ontology for Generalised Multi-Agent Teaming, Onto4MAT, to enable more effective teaming between humans and teams through the biologically-inspired approach of shepherding.

show abstract

Section: Designing An Ontology For Generalised Multi-agent Teamingmentioning

confidence: 97%

Onto4MAT: A Swarm Shepherding Ontology for Generalised Multi-Agent Teaming

Hepworth¹,

Baxter²,

Abbass³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, communication issues impose limits on the amount and speed of information exchange between the human and the swarm. These issues can lead to increased complexity in scenarios where human actions might be based on outdated or incomplete information about the swarm ( Hepworth et al, 2021 ).…”

Section: Mission Complexitymentioning

confidence: 99%

Characterization of Indicators for Adaptive Human-Swarm Teaming

et al. 2022

Self Cite

View full text Add to dashboard Cite

Swarm systems consist of large numbers of agents that collaborate autonomously. With an appropriate level of human control, swarm systems could be applied in a variety of contexts ranging from urban search and rescue situations to cyber defence. However, the successful deployment of the swarm in such applications is conditioned by the effective coupling between human and swarm. While adaptive autonomy promises to provide enhanced performance in human-machine interaction, distinct factors must be considered for its implementation within human-swarm interaction. This paper reviews the multidisciplinary literature on different aspects contributing to the facilitation of adaptive autonomy in human-swarm interaction. Specifically, five aspects that are necessary for an adaptive agent to operate properly are considered and discussed, including mission objectives, interaction, mission complexity, automation levels, and human states. We distill the corresponding indicators in each of the five aspects, and propose a framework, named MICAH (i.e., Mission-Interaction-Complexity-Automation-Human), which maps the primitive state indicators needed for adaptive human-swarm teaming.

show abstract

“…The former allows mutual understanding of the messages, while the latter allows mutual understanding of the rationales behind actions and decisions. Interpretability, explainability and predictability form the tenets for transparency [14] and augment the human user with a better ability to direct/re-direct AIAS as priorities change [15] The effectiveness of observability and directability affords the foundations for trust to emerge among the players; that is, humans trust the AIAS and the AIAS trust humans [16]. Humans tend to retract delegation and assume control (tele-operation) when they lose trust in the automated elements [17].…”

Section: Definition 21 (Symbiomemesis)mentioning

confidence: 99%

“…In symbiomemesis, an increase in latency increases an agent's requirement for prediction and predictability. A sender that changes its states faster than a recipient's ability to receive and decode the messages needs to be more predictable to the recipient to compensate for the uncertainty caused by latency [14]. Moreover, previous research has demonstrated that latency increases human cognitive load [52].…”

Section: Communicationmentioning

confidence: 99%

See 1 more Smart Citation

A model of symbiomemesis: machine education and communication as pillars for human-autonomy symbiosis

Abbass

Petraki

Hussein

et al. 2021

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

Symbiosis is a physiological phenomenon where organisms of different species develop social interdependencies through partnerships. Artificial agents need mechanisms to build their capacity to develop symbiotic relationships. In this paper, we discuss two pillars for these mechanisms: machine education (ME) and bi-directional communication. ME is a new revolution in artificial intelligence (AI) which aims at structuring the learning journey of AI-enabled autonomous systems. In addition to the design of a systematic curriculum, ME embeds the body of knowledge necessary for the social integration of AI, such as ethics, moral values and trust, into the evolutionary design and learning of the AI. ME promises to equip AI with skills to be ready to develop logic-based symbiosis with humans and in a manner that leads to a trustworthy and effective steady-state through the mental interaction between humans and autonomy; a state we name symbiomemesis to differentiate it from ecological symbiosis. The second pillar, bi-directional communication as a discourse enables information to flow between the AI systems and humans. We combine machine education and communication theory as the two prerequisites for symbiosis of AI agents and present a formal computational model of symbiomemesis to enable symbiotic human-autonomy teaming. This article is part of the theme issue ‘Towards symbiotic autonomous systems’.

show abstract

Human-Swarm-Teaming Transparency and Trust Architecture

Cited by 28 publications

References 85 publications

Onto4MAT: A Swarm Shepherding Ontology for Generalised Multi-Agent Teaming

Onto4MAT: A Swarm Shepherding Ontology for Generalised Multi-Agent Teaming

Characterization of Indicators for Adaptive Human-Swarm Teaming

A model of symbiomemesis: machine education and communication as pillars for human-autonomy symbiosis

Contact Info

Product

Resources

About