Adaptive Human-Swarm Interaction based on Workload Measurement using Functional Near-Infrared Spectroscopy

TL;DR

The paper addresses workload management in human-swarm interaction by proposing a real-time, fNIRS-based workload measurement framework. It develops an adaptive HARIS interface using a heatmap abstraction and tests feasibility with a single participant, measuring frontal cortex HbO changes and analyzing with a GLM via the NIRS Toolbox. Key findings indicate detectable HbO variations in the prefrontal cortex linked to workload and demonstrate the feasibility of objective workload monitoring in HSI, while highlighting challenges such as motion, environment, and individual variability. The study lays groundwork for real-time, workload-driven interface adaptation to enhance performance and safety in swarm robotics, with future work focusing on baselines, calibration, and broader validation.

Abstract

One of the challenges of human-swarm interaction (HSI) is how to manage the operator's workload. In order to do this, we propose a novel neurofeedback technique for the real-time measurement of workload using functional near-infrared spectroscopy (fNIRS). The objective is to develop a baseline for workload measurement in human-swarm interaction using fNIRS and to develop an interface that dynamically adapts to the operator's workload. The proposed method consists of using fNIRS device to measure brain activity, process this through a machine learning algorithm, and pass it on to the HSI interface. By dynamically adapting the HSI interface, the swarm operator's workload could be reduced and the performance improved.

Figures (2)

• Figure 1: Heatmap showing abstracted tasks and agent distribution to reduce operator workload.
• Figure 2: Changes in HbO concentrations across prefrontal channels during interactions with the HARIS heatmap interface, as identified by fNIRS contrast analysis. The intensity of blue on a colour scale reflects the magnitude of these changes being statistically significant.