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

arXiv: https://arxiv.org/abs/2209.02886 · HTML: https://mlsanity.com/paper/2209.02886/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 76 references that are in the map.
- First posted on arXiv 7 Sep 2022.

## Builds on (most cited first, 16 of 16)

- [Self-Driving Cars: A Survey](https://mlsanity.com/paper/1901.04407/) (2019)
- [Behavior Trees in Robotics and AI: An Introduction](https://mlsanity.com/paper/1709.00084/) (2017)
- [A Survey of Behavior Trees in Robotics and AI](https://mlsanity.com/paper/2005.05842/) (2020)
- [Human-Centered Artificial Intelligence and Machine Learning](https://mlsanity.com/paper/1901.11184/) (2019)
- [Learning of Behavior Trees for Autonomous Agents](https://mlsanity.com/paper/1504.05811/) (2015)
- [Needs-driven Heterogeneous Multi-Robot Cooperation in Rescue Missions](https://mlsanity.com/paper/2009.00288/) (2020)
- [Behavior Trees in Action: A Study of Robotics Applications](https://mlsanity.com/paper/2010.06256/) (2020)
- [Combining Planning and Learning of Behavior Trees for Robotic Assembly](https://mlsanity.com/paper/2103.09036/) (2021)
- [Reactive Task and Motion Planning under Temporal Logic Specifications](https://mlsanity.com/paper/2103.14464/) (2021)
- [Parallel Knowledge Transfer in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.13085/) (2020)
- [Learning and Executing Re-usable Behaviour Trees from Natural Language Instruction](https://mlsanity.com/paper/2106.01650/) (2021)
- [Game-theoretic Utility Tree for Multi-Robot Cooperative Pursuit Strategy](https://mlsanity.com/paper/2206.01109/) (2022)
- [Multi-agent Reinforcement Learning with Sparse Interactions by Negotiation and Knowledge Transfer](https://mlsanity.com/paper/1508.05328/) (2015)
- [SO-MRS: a multi-robot system architecture based on the SOA paradigm and ontology](https://mlsanity.com/paper/1709.03300/) (2017)
- [Impact of Heterogeneity in Multi-Robot Systems on Collective Behaviors Studied Using a Search and Rescue Problem](https://mlsanity.com/paper/2012.14329/) (2020)
- [Handling Concurrency in Behavior Trees](https://mlsanity.com/paper/2110.11813/) (2021)

## Built on by (most cited first, 6 of 6)

- [Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy](https://mlsanity.com/paper/2503.10049/) (2025)
- [Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2310.08565/) (2023)
- [HARMONIC: A Framework for Explanatory Cognitive Robots](https://mlsanity.com/paper/2409.18037/) (2024)
- [HARMONIC: Cognitive and Control Collaboration in Human-Robotic Teams](https://mlsanity.com/paper/2409.18047/) (2024)
- [HARMONIC: A Content-Centric Cognitive Robotic Architecture](https://mlsanity.com/paper/2509.13279/) (2025)
- [Transforming Monolithic Foundation Models into Embodied Multi-Agent Architectures for Human-Robot Collaboration](https://mlsanity.com/paper/2512.00797/) (2025)

## Abstract (arXiv)

Multi-Robot and Multi-Agent Systems demonstrate collective (swarm) intelligence through systematic and distributed integration of local behaviors in a group. Agents sharing knowledge about the mission and environment can enhance performance at individual and mission levels. However, this is difficult to achieve, partly due to the lack of a generic framework for transferring part of the known knowledge (behaviors) between agents. This paper presents a new knowledge representation framework and a transfer strategy called KT-BT: Knowledge Transfer through Behavior Trees. The KT-BT framework follows a query-response-update mechanism through an online Behavior Tree framework, where agents broadcast queries for unknown conditions and respond with appropriate knowledge using a condition-action-control sub-flow. We embed a novel grammar structure called stringBT that encodes knowledge, enabling behavior sharing. We theoretically investigate the properties of the KT-BT framework in achieving homogeneity of high knowledge across the entire group compared to a heterogeneous system without the capability of sharing their knowledge. We extensively verify our framework in a simulated multi-robot search and rescue problem. The results show successful knowledge transfers and improved group performance in various scenarios. We further study the effects of opportunities and communication range on group performance, knowledge spread, and functional heterogeneity in a group of agents, presenting interesting insights.