# From Network Sensors to Intelligent Systems: A Decade-Long Review of Swarm Robotics Technologies

## TL;DR

This paper reviews advancements in swarm robotics over the past decade, highlighting progress in hardware and software while identifying challenges like standardization and scalability.

## Contribution

The paper provides a systematic literature review of swarm robotics technologies from 2014 to 2024, emphasizing co-evolution of hardware and software subsystems.

## Key findings

- Swarm robotics hardware and software have co-evolved, but lack of uniform standards hinders progress.
- Sensor hardware, actuation methods, and communication devices show significant trends but face scalability issues.
- Integration of machine learning is proposed as a future direction for improving swarm robotics systems.

## Abstract

Swarm Robotics (SR) is a relatively new field, inspired by the collective intelligence of social insects. It involves using local rules to control and coordinate large groups (swarms) of relatively simple physical robots. Important tasks that robot swarms can handle include demining, search, rescue, and cleaning up toxic spills. Over the past decade, the research effort in the field of Swarm Robotics has intensified significantly in terms of hardware, software, and systems integrated developments, yet significant challenges remain, particularly regarding standardization, scalability, and cost-effective deployment. To contextualize the state of Swarm Robotics technologies, this paper provides a systematic literature review (SLR) of Swarm Robotic technologies published from 2014 to 2024, with an emphasis on how hardware and software subsystems have co-evolved. This work provides an overview of 40 studies in peer-reviewed journals along with a well-defined and replicable systematic review protocol. The protocol describes criteria for including and excluding studies and outlines a data extraction approach. We explored trends in sensor hardware, actuation methods, communication devices, and energy systems, as well as an examination of software platforms to produce swarm behavior, covering meta-heuristic algorithms and generic middleware platforms such as ROS. Our results demonstrate how dependent hardware and software are to achieve Swarm Intelligence, the lack of uniform standards for their design, and the pragmatic limits which hinder scalability and deployment. We conclude by noting ongoing challenges and proposing future directions for developing interoperable, energy-efficient Swarm Robotics (SR) systems incorporating machine learning (ML).