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

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

    Sep 15, 2026Antonio Alvarez Valdivia, Ciera McFarland, Robert Reeve +5RoboticsSearch-and-Rescue Robotics

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

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

    Aug 30, 2026Alice Mylaeus, Stephanie Vogt, Berken Utku Demirel +4Assistive RoboticsSoft Robotics

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

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

    Jun 16, 2026Milind Rampure, Shadman Sakib, Haley Patel +2Multimodal Sensor Fusion

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