Toward a Wearable Biosensor Ecosystem on ROS 2 for Real-time Human-Robot Interaction Systems
This work addresses the problem of extraneous complexity and limited collaboration in HRI systems for researchers and developers, though it is incremental as it builds on existing ROS 2 infrastructure.
The authors tackled the lack of standardized libraries for integrating wearable biosensors into human-robot interaction systems by introducing a novel package for ROS 2, which standardizes biosensor integration and lowers technical barriers, with the package made publicly available on GitHub.
Wearable biosensors can enable continuous human data capture, facilitating development of real-world Human-Robot Interaction (HRI) systems. However, a lack of standardized libraries and implementations adds extraneous complexity to HRI system designs, and precludes collaboration across disciplines and institutions. Here, we introduce a novel wearable biosensor package for the Robot Operating System 2 (ROS 2) system. The ROS2 officially supports real-time computing and multi-robot systems, and thus provides easy-to-use and reliable streaming data from multiple nodes. The package standardizes biosensor HRI integration, lowers the technical barrier of entry, and expands the biosensor ecosystem into the robotics field. Each biosensor package node follows a generalized node and topic structure concentrated on ease of use. Current package capabilities, listed by biosensor, highlight package standardization. Collected example data demonstrate a full integration of each biosensor into ROS2. We expect that standardization of this biosensors package for ROS2 will greatly simplify use and cross-collaboration across many disciplines. The wearable biosensor package is made publicly available on GitHub at \https://github.com/SMARTlab-Purdue/ros2-foxy-wearable-biosensors.