cs.ROApr 1, 2026

An Integrated Soft Robotic System for Measuring Vital Signs in Search and Rescue Environments

Authors: Jorge Francisco García-Samartín, Christyan Cruz Ulloa, Andrés Sánchez-Silva, Jaime del Cerro, Antonio Barrientos

Organizations: Centro de Automática y Robótica (UPM - CSIC), Universidad Politécnica de Madrid, Calle José Gutiérrez Abascal 2, 28006, Madrid, Spain

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Robots are frequently utilized in search-and-rescue operations. In recent years, significant advancements have been made in the field of victim assessment. However, there are still open issues regarding heart rate measurement, and no studies have been found that assess pressure in post-disaster scenarios. This work designs a soft gripper and integrates it into a mobile robotic system, thereby creating a device capable of measuring the pulse and blood pressure of victims in post-disaster environments. The gripper is designed to envelop the victim's arm and inflate like a sphygmomanometer, facilitated by a specialized portability system. The utilization of different signal processing algorithms has enabled the attainment of a pulse bias of \qty{4}{\bpm} and a bias of approximately \qty{5}{\mmHg} for systolic and diastolic pressures. The findings, in conjunction with the other statistical data and the validation of homoscedasticity in the error terms, prove the system's capacity to accurately determine heart rate and blood pressure, thereby rendering it suitable for search and rescue operations. Finally, a post-disaster has been employed as a test to validate the functionality of the entire system and to demonstrate its capacity to adapt to various victim positions, its measurement speed, and its safety for victims.

Figures & tables

Figure 1: Diagram of the system architecture.
Figure 2: Design and components of the pneumatic gripper subsystem: a) Picture of the subsystem. b) Components of the clamp. c) Section of the inflatable module of the clamp. d) Connection between the electronics case, where the pneumatic feed tube passes through, and the first segment of the inflatable module.
Figure 3: Schematic diagram of the system measurement elements.
Figure 4: Schematic diagram of the pneumatic system.
Figure 5: Functionality of the pneumatic system. a) Actuator closure. b) Actuator opening. c) Pressure measurement. d) Process of inflating and deflating the clamp and cuff.
SensorInterval ( ms\mathrm{ms} )Frequency ( Hz\mathrm{Hz} )
Pressure (clamp)10100
Pressure (cuff)10100
Pulse4025
Table 1: Sensor sampling frequencies
Figure 6: Pulse signal processing stages: a) Low-pass filtering at 3.5 Hz3.5\text{\,}\mathrm{Hz} of the complete pulse signal. b) Systolic peaks detected in the first phase. c) Systolic peaks detected after applying the adaptive filter based on prominence.
Figure 7: Comparison between the original pressure signal and its filtered version.
Figure 8: Peaks detected after morphological filtering.
Figure 9: Histogram of the distances (in number of samples) between consecutive peaks.
Figure 10: Peaks detected after distance filtering.
Figure 11: Original and smoothed amplitudes and location of MAP.
Figure 12: Graphs of the pressure signal and its derivative, showing the blood pressure values obtained and all the peaks analyzed.
 MAERMSEMedAE% Error (MAE)
Pulse9.63 bpm9.63\text{\,}\mathrm{bpm}14.93 bpm14.93\text{\,}\mathrm{bpm}7.00 bpm7.00\text{\,}\mathrm{bpm}13.18 %
Pulse (w/o outlier)7.20 bpm7.20\text{\,}\mathrm{bpm}9.20 bpm9.20\text{\,}\mathrm{bpm}6.00 bpm6.00\text{\,}\mathrm{bpm}9.5 %
Systolic Pressure12.06 mmHg12.06\text{\,}\mathrm{mmHg}16.00 mmHg16.00\text{\,}\mathrm{mmHg}9.67 mmHg9.67\text{\,}\mathrm{mmHg}10.65 %
Diastolic Pressure9.50 mmHg9.50\text{\,}\mathrm{mmHg}12.22 mmHg12.22\text{\,}\mathrm{mmHg}8.00 mmHg8.00\text{\,}\mathrm{mmHg}13.01 %
Table 2: Errors in pulse and blood pressure measurement
ParameterBiasSDLoA lowLoA high
Pulse−-6.68\text{,}\mathrm{bpm}$$13.69 bpm13.69\text{\,}\mathrm{bpm}−-33.52\text{,}\mathrm{bpm}$$20.16 bpm20.16\text{\,}\mathrm{bpm}
Systolic Pressure−-6.07\text{,}\mathrm{mmHg}$$15.19 mmHg15.19\text{\,}\mathrm{mmHg}−-35.84\text{,}\mathrm{mmHg}$$23.70 mmHg23.70\text{\,}\mathrm{mmHg}
Diastolic Pressure−-6.92\text{,}\mathrm{mmHg}$$10.33 mmHg10.33\text{\,}\mathrm{mmHg}−-27.16\text{,}\mathrm{mmHg}$$13.33 mmHg13.33\text{\,}\mathrm{mmHg}
Table 3: Agreement analysis between the robotic system and the reference sphygmomanometer.
ParameterBiasSDLoA lowLoA high
Pulse- 4.21 bpm4.21\text{\,}\mathrm{bpm}7.37 bpm7.37\text{\,}\mathrm{bpm}- 18.65 bpm18.65\text{\,}\mathrm{bpm}10.22 bpm10.22\text{\,}\mathrm{bpm}
Systolic Pressure- 4.94 mmHg4.94\text{\,}\mathrm{mmHg}11.71 mmHg11.71\text{\,}\mathrm{mmHg}- 27.88 mmHg27.88\text{\,}\mathrm{mmHg}17.99 mmHg17.99\text{\,}\mathrm{mmHg}
Diastolic Pressure- 6.25 mmHg6.25\text{\,}\mathrm{mmHg}9.46 mmHg9.46\text{\,}\mathrm{mmHg}- 24.79 mmHg24.79\text{\,}\mathrm{mmHg}12.29 mmHg12.29\text{\,}\mathrm{mmHg}
Table 4: Agreement analysis between the robotic system and the reference sphygmomanometer after removing the outlier of the element N=14.
Figure 13: Bland-Altman plots for the experiments of A) Pulse. B) Systolic pressure. C) Diastolic pressure.
Figure 14: Validation scenario and tests: a) Post-disaster scenario used for validation. Green arrows indicate the presence of a human victim, while yellow arrows indicate the presence of a mannequin. The position of the victim (seated or lying down) is specified by the letter inside the arrow. b) Complete system setup for validation. c) System measuring vital signs to a victim.
More in this topic

Heart Rate Estimation

Heart rate estimation recovers beats per minute from wearable, contact, or remote physiological signals.

See all 31 papers

Explore similar work

CardsList
Sep 15, 2026

SPROUT: The Open-Source Soft Growing Robot for Search and Rescue

Soft robotic systems have long been theorized as ideal candidates for use in search and rescue operations; however, there have been significant barriers to entry in graduating soft robotic systems from the laboratory to the field. To address this gap in replicable, reliable soft robot systems, we present the designs for SPROUT, the Soft Pathfinding Robotic Observation Unit. The system has matured over years of interaction with professional urban search and rescue communities, with the goal of operating in dusty, wet, and isolated conditions. This manuscript contains supplementary material, including code, parts manifests, CAD assemblies, and build instructions to allow the broader robotics research community to build their own SPROUT systems. The modular hardware and ROS 2-based software stack support task-specific payloads and control functions, allowing SPROUT to be adapted for applications beyond search and rescue, including infrastructure inspection and archaeology. Here, we demonstrate SPROUT performing a variety of challenging inspection and traversal tasks in collapsed structure training sites used by first responders. The main project page is available online at https://sprout-mitll.github.io/sprout/.

Antonio Alvarez Valdivia, Ciera McFarland, Robert Reeve +5

Lincoln Laboratory, Massachusetts Institute of Technology, Lexington, Massachusetts, USA · University of Notre Dame, Notre Dame, Indiana, USA · Stanford University, Stanford, California, USA

RoboticsSearch-and-Rescue RoboticsSoft Robotics
AskPDF
Aug 30, 2026

MiBOT: A head-worn robot that modulates cardiovascular responses through human-like soft massage

Massage therapy is helpful for the rehabilitation of various diseases, such as headaches caused by migraines and stress. Existing robotic systems have focused on massage therapy on the torso and limbs, but performing massage motions through suitable actuation on a person's head has been a challenge. In this paper, we present MiBOT, a head-worn massage robot that actuates two soft tactors to produce touch motions mimicking human massage. A key design principle behind MiBOT is its silent actuation, which we achieve through pneumatic artificial muscles in conjunction with a controller loop to respond to contact pressure. We evaluated the effectiveness of MiBOT in a controlled study and assessed subjects' blood pressure and heart rate levels while applying MiBOT. We found that our mechanical system generated positive and conclusive quantitative outcomes that are similar to the human-administered massage, decreasing participants' mean systolic and diastolic blood pressure by 2.8 mmHg and 1.7 mmHg, respectively, as well as calming their heart rate by 8-10% on average.

Alice Mylaeus, Stephanie Vogt, Berken Utku Demirel +4

Department of Computer Science, ETH Zürich, Switzerland. · Department of Mechanical Engineering, ETH Zürich, Switzerland.

Assistive RoboticsSoft Robotics
AskPDF
Jun 16, 2026

Contactless Respiratory Monitoring on Heterogeneous Mobile Robots: A Multimodal Edge-Computing Framework

Respiratory-rate (RR) monitoring is a critical component of remote triage and victim assessment in emergency response, disaster recovery, and infectious-disease scenarios, where minimizing physical contact can reduce responder risk and improve operational safety. However, field deployment of contactless RR monitoring remains challenging due to variable illumination, posture changes, platform heterogeneity, and the impracticality of wearable sensors in hazardous environments. In this paper, we present a modality-adaptive contactless RR monitoring framework for heterogeneous mobile robots with onboard edge computing. The proposed system combines brightness-adaptive sensor selection across RGB, thermal, near-infrared (NIR), and low-light cameras, keypoint-guided chest ROI extraction for posture-robust monitoring, and a signal-quality-index (SQI)-based filtering mechanism for reliable respiratory estimation. We implement and evaluate the framework on three robotic platforms spanning quadruped and wheeled locomotion and multiple edge-computing architectures. Experiments conducted across diverse lighting conditions, subject poses, and robot-to-subject distances demonstrate that the framework generalizes across platforms without per-platform algorithmic retuning, while revealing modality-specific operational boundaries. RGB provides the broadest coverage up to 8m, NIR remains effective up to 6m, thermal is reliable only at short range, and low-light sensing supports monitoring in complete darkness up to 8m. Overall, the results demonstrate the feasibility of multimodal contactless RR monitoring on mobile robots and support its use as a foundation for autonomous triage and victim assessment in hazardous search-and-rescue settings.

Milind Rampure, Shadman Sakib, Haley Patel +2

Department of Information Systems, University of Maryland Baltimore County, USA · Department of Computer Science, University of Maryland Baltimore County, USA

Multimodal Sensor Fusion
AskPDF