Sense4HRI: A ROS 2 HRI Framework for Physiological Sensor Integration and Synchronized Logging

Manuel Scheibl; Julian Leichert; Sinem Görmez; Britta Wrede

cs.HCMar 20, 2026

Sense4HRI: A ROS 2 HRI Framework for Physiological Sensor Integration and Synchronized Logging

Authors: Manuel Scheibl, Julian Leichert, Sinem Görmez, Britta Wrede

Organizations: Medical Assistance Systems, Medical School OWL, Bielefeld University, 33501 Bielefeld, Germany · Center for Cognitive Interaction Technology, CITEC from Bielefeld University, Germany

Abstract

Physiological signals are increasingly relevant to estimate the mental states of users in human-robot interaction (HRI), yet ROS 2-based HRI frameworks still lack reusable support to integrate such data streams in a standardized way. Therefore, we propose Sense4HRI, an adapted framework for human-robot interaction in ROS 2 that integrates physiological measurements and derived user-state indicators. The framework is designed to be extensible, allowing the integration of additional physiological sensors, their interpretation, and multimodal fusion to provide a robust assessment of the mental states of users. In addition, it introduces reusable interfaces for timestamped physiological time-series data and supports synchronized logging of physiological signals together with experiment context, enabling interoperable and traceable multimodal analysis within ROS 2-based HRI systems.

Figures & tables

Sensor Type	Measurement	Indicative of
EEG	Multi-Channel Brain Activity [ 3 ]	Workload [ 3 ] ; Stress
PPG	Variations in blood volume [ 3 ]	Anxiety; cognitive effort [ 15 ]
ECG	Electrical activity of the heart [ 3 ]	Mental and Emotional Stress [ 16 , 17 , 18 ] ; Physical Effort [ 19 ]
Skin Conductance	Electrical conductivity of the skin	Emotional arousal; mental load [ 3 ]
EMG	Electrical activity generated by skeletal muscles [ 3 ]	motor control / motor intention [ 3 ]
Eye Tracking	Visual attention and gaze behavior [ 3 ]	Attention [ 3 ] ; engagement [ 20 ] ; intention [ 21 ]

TABLE I: Overview of physiological sensors used in HRI.

Fig. 1: Schematic overview of the physiological sensing pipeline used in this work. Left: exemplary body locations of the considered sensor modalities. Middle: corresponding primary (raw) measurements. Right: high-level indicator categories for which each modality can provide evidence. Crosses indicate a non-exclusive mapping (i.e., a sensor may inform multiple categories and categories may be supported by multiple sensors).

Fig. 2: Overview of the proposed ROS 2 architecture for physiological sensing (left) and detailed structure of PhysioRaw.msg (right). A sensor driver node wraps the physiological device and publishes raw measurements as PhysioRaw.msg , which can be consumed directly by applications or processed by an interpreter node for sensor-specific preprocessing and feature extraction. The architecture further supports device-level feature messages ( PhysioDeviceFeature.msg ) and processed sensor-specific outputs ( <SensorType>.msg ). The PhysioRaw.msg message comprises ROS metadata ( header ), a device-side timestamp ( device_timestamp ), and an array of PhysioRawChannel elements containing channel names and floating-point sample arrays.

Fig. 3: Web GUI for real-time physiological sensor data visualization.

Explore similar work

Establishing a Dynamic Multimodal HRI Dataset for Engagement Analysis with a Humanoid Robot
Sep 3, 2026Buwan Kim, Wonse JoRobotic Data Collection Human-Robot Interaction
Department of Information and Telecommunication Engineering, Incheon National University, Incheon, South Korea 22012.
OpenRoIS: A Community-Driven Open-Source Middleware Implementing the Robotic Interaction Service (RoIS) Framework for Physical Robots and Virtual Agents
Sep 18, 2026Sebastian Carrera Villalobos, Christopher Nolan Arellano, Arne Hitzmann +5Robotics Human-Robot Interaction
Coarobo GK · The University of Texas at Austin, 110 Inner Campus Drive, Austin, Texas 78712, United States · Advanced Telecommunications Research Institute International (ATR), 2-2-2 Hikaridai, Seika, Soraku, Kyoto 619-0288, Japan
Augmented Reality Interfaces for Human-Robot Collaboration: Development of a ROS 2-Based Sensor Streaming Framework and Validation via SLAM Algorithms
Sep 25, 2026Alessandro Rubert, Stefano Ghidoni, Matteo TerreranRobotics Human-Robot Collaboration
DEPARTMENT OF INFORMATION ENGINEERING

Sep 3, 2026J/K move · Enter open · S save

Establishing a Dynamic Multimodal HRI Dataset for Engagement Analysis with a Humanoid Robot

Buwan Kim, Wonse Jo

Department of Information and Telecommunication Engineering, Incheon National University, Incheon, South Korea 22012.

Robotic Data Collection Human-Robot Interaction

Open paper AskPDF arXiv

This paper presents an experimental design for constructing a multimodal dataset to analyze user engagement in human-robot interaction (HRI). Prior studies have mainly relied on observable behavioral cues, with limited frameworks integrating physiological signals. We therefore propose a structured data-collection protocol to build a multimodal dataset that includes wearable physiological signals, behavioral data, and self-report measures under different levels of task complexity defined in this experiment.

Abstract

Explore similar work

Establishing a Dynamic Multimodal HRI Dataset for Engagement Analysis with a Humanoid Robot

OpenRoIS: A Community-Driven Open-Source Middleware Implementing the Robotic Interaction Service (RoIS) Framework for Physical Robots and Virtual Agents

Augmented Reality Interfaces for Human-Robot Collaboration: Development of a ROS 2-Based Sensor Streaming Framework and Validation via SLAM Algorithms