Infra-Swarm: Robust Vision-Based Multi-Robot Swarming via Near-Infrared Spectral Vision

2026-07-14

AI Summary

This work addresses the susceptibility of multi-robot swarms to bandwidth constraints and environmental lighting interference when relying on wireless communication or visible-light vision. To overcome these limitations, the authors propose Infra-Swarm, a novel system that leverages a 940 nm near-infrared light source and a quad grayscale camera array to achieve communication-free, centimeter-accurate 3D relative localization. By modeling the position and intensity of optical glare and employing narrowband optical filtering to physically suppress 99.2% of ambient light interference, the system maintains robust perception under drastic illumination changes. Furthermore, it significantly reduces computational overhead, offering a scalable and low-power perceptual foundation suitable for large-scale swarms operating on resource-constrained platforms.

Abstract

Distributed swarms typically rely on either active wireless communication or passive vision, and they are frequently hindered by bandwidth constraints or environmental sensitivity. This paper proposes Infra-Swarm, a robust vision-based swarm. Each robot is equipped with a near-infrared light source and four ordinary gray-scale cameras. The Infra-Swarm system directly measures the centimeter-level 3D position of neighbors based on the position (bearing) and intensity (strength) of optical flares in the captured images. By utilizing 940 nm narrow-band filters to physically reject 99.2% of ambient light interference, the perception front-end achieves hardware-level robustness against illumination variations. Furthermore, its minimal computational overhead provides a resilient foundation for the massive scalability of robotic collectives on resource-constrained hardware.

Problem

• multi-robot swarming
• vision-based perception
• near-infrared vision
• ambient light interference
• scalability

Innovation

• near-infrared vision
• vision-based swarming
• optical flare localization
• ambient light rejection
• resource-constrained robotics