# Contextually Aware Intelligent Control Agents for Heterogeneous Swarms

arXiv: https://arxiv.org/abs/2211.12560 · HTML: https://mlsanity.com/paper/2211.12560/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 61 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 9 of 9)

- [A Comprehensive Review of Shepherding as a Bio-inspired Swarm-Robotics Guidance Approach](https://mlsanity.com/paper/1912.07796/) (2019)
- [Herding stochastic autonomous agents via local control rules and online global target selection strategies](https://mlsanity.com/paper/2010.00386/) (2020)
- [Learning to Herd Agents Amongst Obstacles: Training Robust Shepherding Behaviors using Deep Reinforcement Learning](https://mlsanity.com/paper/2005.09476/) (2020)
- [Onto4MAT: A Swarm Shepherding Ontology for Generalised Multi-Agent Teaming](https://mlsanity.com/paper/2203.12955/) (2022)
- [Context-Aware Deep Q-Network for Decentralized Cooperative Reconnaissance by a Robotic Swarm](https://mlsanity.com/paper/2001.11710/) (2020)
- [Bio-Inspired Local Information-Based Control for Probabilistic Swarm Distribution Guidance](https://mlsanity.com/paper/1711.06869/) (2017)
- [Lifelong Testing of Smart Autonomous Systems by Shepherding a Swarm of Watchdog Artificial Intelligence Agents](https://mlsanity.com/paper/1812.08960/) (2018)
- [Hierarchical Control of Smart Particle Swarms](https://mlsanity.com/paper/2204.07195/) (2022)
- [Swarm Analytics: Designing Information Markers to Characterise Swarm Systems in Shepherding Contexts](https://mlsanity.com/paper/2208.12386/) (2022)

## Abstract (arXiv)

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.