Activity Recognition for Shepherding

Hepworth, Adam J.

doi:10.1007/978-3-030-60898-9_7

Cited by 5 publications

(8 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Agent class focuses on the representation of an agent fulfilling one of three primary types in a shepherding situation, being that of the shepherd (commander, ζ), the sheepdog (shepherding control agent, β), and the sheep (team member, π) [14]. Note that we include the ability to define an artificial type of agent here, available to fulfil any of the three primary types.…”

Section: ) Agentmentioning

confidence: 99%

“…When an intent is sufficiently and successfully transferred from one agent to another, intent enables the receiving agent to develop their sequence of actions to achieve an outcome. From a recognition perspective, observing actions and tactics may enable the inference of an intent to generate higher situational and context awareness [12], [14]. In Onto4MAT, the class Intent is a primitive which provides rich semantics to the upper-level ontology.…”

Section: ) Intentmentioning

confidence: 99%

“…Humans may need to guide the swarm, and an external entity may VOLUME ?, 2022 need to guide the teaming arrangements among the humans and the swarm. Shepherding is a biologically-inspired swarm guidance and control technique [12], [13]), whereby one or a few powerful cognitive agents guide a larger group of potentially less-powerful agents, similarly to that of a sheepdog guiding a flock of sheep [14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Onto4MAT: A Swarm Shepherding Ontology for Generalized Multiagent Teaming

2022

Self Cite

View full text Add to dashboard Cite

Research in multi-agent teaming has increased substantially over recent years. Underneath these attempts sits a suite of communication functions to enable effective teaming. The Artificial Intelligence (AI) systems supporting the teaming arrangement have mostly relied on knowledge-based systems, with a set of rules triggered based on mode of interaction. Enabling humans to effectively join the team of AI agents calls for both the humans and AI agents to share their understanding and representation of their shared worlds. Such shared understanding requires formal representations of concepts to support transparency during bi-directional communications between team members. Little research has been done in this space, especially when humans need to team with a swarm of agents. To address this research gap, we present an ontology designed specifically for human-agent teaming. The ontology is general, but we then contextualise it into a particular swarm-shepherding scenario to illustrate how it can be used in a particular context. The proposed Ontology for Generalised Multi-Agent Teaming Onto4MAT offers the underlying building blocks for effective communication and shared understanding between humans and multi-agent teams.

show abstract

Section: ) Agentmentioning

confidence: 99%

Section: ) Intentmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Onto4MAT: A Swarm Shepherding Ontology for Generalized Multiagent Teaming

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Humans may need to guide the swarm, and an external entity may need to guide the teaming arrangements among the humans and the swarm. Shepherding is a biologically-inspired swarm guidance and control technique [12,13]), whereby one or a few powerful cognitive agents guide a larger group of potentially lesspowerful agents, similarly to that of a sheepdog guiding a flock of sheep [14].…”

Section: Introductionmentioning

confidence: 99%

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

“…These models often use static behaviour selection policies for the control agent to guide a swarm to a goal location Debie et al (2021). As a biologically-inspired approach to swarm control, shepherding has applications across different domains, such as the guidance and control of crowds Li, Hu, Liang, and Li (2012), herding biological animals Paranjape, Chung, Kim, and Shim (2018), guiding teams of uncrewed system (UxS) Hepworth (2021), and controlling a group of robotic platforms Cowling and Gmeinwieser (2010); Lee and Kim (2017).…”

Section: Introductionmentioning

confidence: 99%

Contextually Aware Intelligent Control Agents for Heterogeneous Swarms

Hepworth

Hussein

Reid

et al. 2022

Preprint

View full text Add to dashboard Cite

An emerging challenge in swarm shepherding research is to design effective and efficient artificial intelligence algorithms that maintain a low-computational ceiling while increasing the swarm's abilities to operate in diverse contexts. We propose a methodology to design a context-aware swarm-control intelligent agent. The intelligent control agent (shepherd) first uses swarm metrics to recognise the type of swarm it interacts with to then select a suitable parameterisation from its behavioural library for that particular swarm type. The design principle of our methodology is to increase the situation awareness (i.e. information contents) of the control agent without sacrificing the low-computational cost necessary for efficient swarm control. We demonstrate successful shepherding in both homogeneous and heterogeneous swarms.

show abstract

Activity Recognition for Shepherding

Cited by 5 publications

References 63 publications

Onto4MAT: A Swarm Shepherding Ontology for Generalized Multiagent Teaming

Onto4MAT: A Swarm Shepherding Ontology for Generalized Multiagent Teaming

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

Contextually Aware Intelligent Control Agents for Heterogeneous Swarms

Contact Info

Product

Resources

About