English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Multi-Robot and Multi-Agent Systems demonstrate collective (swarm)intelligence through systematic and distributed integration of local behaviorsin a group. Agents sharing knowledge about the mission and environment canenhance performance at individual and mission levels. However, this isdifficult to achieve, partly due to the lack of a generic framework fortransferring part of the known knowledge (behaviors) between agents. This paperpresents a new knowledge representation framework and a transfer strategycalled KT-BT: Knowledge Transfer through Behavior Trees. The KT-BT frameworkfollows a query-response-update mechanism through an online Behavior Treeframework, where agents broadcast queries for unknown conditions and respondwith appropriate knowledge using a condition-action-control sub-flow. We embeda novel grammar structure called stringBT that encodes knowledge, enablingbehavior sharing. We theoretically investigate the properties of the KT-BTframework in achieving homogeneity of high knowledge across the entire groupcompared to a heterogeneous system without the capability of sharing theirknowledge. We extensively verify our framework in a simulated multi-robotsearch and rescue problem. The results show successful knowledge transfers andimproved group performance in various scenarios. We further study the effectsof opportunities and communication range on group performance, knowledgespread, and functional heterogeneity in a group of agents, presentinginteresting insights.

KT-BT: A Framework for Knowledge Transfer Through Behavior Trees in Multi-Robot Systems