CRIS

Permanent URI for this communityhttps://cris.ute.edu.ec/handle/123456789/1

Browse

Search Results

Now showing 1 - 4 of 4

Some of the metrics are blocked by your
consent settings
Control Design and Validation of Gait Analysis with the Robogait Mobile Robotic Platform
(Springer Nature Switzerland, 2025-09-03)
GUFFANTI MARTÍNEZ, DIEGO ANDRES
;
Alberto Brunete
;
Miguel Hernando Gutierrez
;
David Álvarez
;
GUTIÉRREZ SUQUILLO, NELSON RAMIRO
The integration of mobile robotic platforms with depth sensors could led to a major advance in human gait analysis. However, the lack of dedicated technologies designed specifically for corridor-based gait analysis limits the availability of comprehensive tools to accurately and efficiently capture and analyze gait data in this specific context. In this study, control algorithms for person following and lane keeping of a mobile robotic platform named Robogait were applied and validated experimentally. The validity of using an Azure Kinect sensor for gait analysis was also examined using gait data collected from 10 participants and comparing its accuracy in gait signals and gait parameters with respect to a Vicon photogrammetric system. Results in controller design demonstrated a path following error of only 0.0446 m was measured on average, with a maximum deviation of 0.1420 m. The person tracking presented slight oscillations, however it did not affect the performance of the system in the gait analysis. An RMSE error of 12.68 was obtained for knee flex./ext., 5.54 for hip flex./ext., and just 0.06 m for the inter-ankle distance. Regarding gait descriptors analyzed, the Azure Kinect system provides reliable gait event measurements, though some discrepancies exist compared to Vicon. This study validates the use of the Azure Kinect sensor in gait analysis with mobile platforms. This offers a low-cost solution in real environments such as hospital corridors, contrary to in-lab gait analysis where the influence of equipment and the controlled environment could alter the gait pattern. The robot setup errors were comparable to static treadmill systems and similar to those of Vicon systems, which highlights its potential in clinical and rehabilitation applications.
Some of the metrics are blocked by your
consent settings
RoboGait: sistema robótico no invasivo para el análisis de la marcha humana
(Universitat Politecnica de Valencia, 2023-10-31)
David Álvarez
;
GUFFANTI MARTINEZ, DIEGO ANDRES
;
Alberto Brunete
;
Miguel Hernando
;
Ernesto Gambao
Actualmente, los sistemas utilizados en laboratorios para analizar la marcha se basan en técnicas marcadores o sensores colocados sobre el cuerpo del paciente, lo que resulta en un proceso que requiere un tiempo largo de preparación y calibración, así como la incomodidad que causa a los pacientes tener dispositivos colocados por el cuerpo. Además, el espacio en el que se pueden realizar pruebas resulta muy limitado. En respuesta a estas problemáticas, se ha desarrollado el sistema robótico RoboGait. Consiste en un robot móvil capaz de navegar autónomamente delante del paciente. El robot incluye una cámara RGBD en su parte superior para captar el cuerpo humano. Este sistema no requiere marcadores adheridos al cuerpo del paciente ya que utiliza la información proporcionada por la cámara RGBD para analizar la marcha. El objetivo de este estudio es demostrar la validez de RoboGait y su aplicabilidad en entornos clínicos. Para conseguirlo, se ha optado por mejorar la estimación de señales cinemáticas y espacio-temporales de la marcha procesando las medidas de la cámara con redes neuronales artificiales (RNA) entrenadas usando datos obtenidos de un sistema Vicon certificado. Posteriormente, se ha medido el rendimiento del sistema en la clasificación de patrones normales y patológicos, utilizando como referencia un sistema basado en sensores inerciales Xsens. De este modo, se ha probado el sistema robótico móvil en un rango amplio de la marcha, al tiempo que se ha comparado con un sistema comercial en las mismas condiciones experimentales. Los resultados obtenidos demuestran que RoboGait puede realizar el análisis de la marcha con suficiente precisión,mostrando un gran potencial para su análisis clínico y la identificación de patologías.
Some of the metrics are blocked by your
consent settings
Supervised learning for improving the accuracy of robot-mounted 3D camera applied to human gait analysis
(Elsevier BV, 2024-02)
GUFFANTI MARTINEZ, DIEGO ANDRES
;
Alberto Brunete
;
Miguel Hernando
;
David Álvarez
;
Javier Rueda
Background and Objective: the use of 3D cameras for gait analysis has been highly questioned due to the low accuracy they have demonstrated in the past. The objective of the study presented in this paper is to improve the accuracy of the estimations made by robot-mounted 3D cameras in human gait analysis by applying a supervised learning stage. Methods: the 3D camera was mounted in a mobile robot to obtain a longer walking distance. This study shows an improvement in detection of kinematic gait signals and gait descriptors by post-processing the raw estimations of the camera using artificial neural networks trained with the data obtained from a certified Vicon system. To achieve this, 37 healthy participants were recruited and data of 207 gait sequences were collected using an Orbbec Astra 3D camera. There are two basic possible approaches for training and both have been studied in order to see which one achieves a better result. The artificial neural network can be trained either to obtain more accurate kinematic gait signals or to improve the gait descriptors obtained after initial processing. The former seeks to improve the waveforms of kinematic gait signals by reducing the error and increasing the correlation with respect to the Vicon system. The second is a more direct approach, focusing on training the artificial neural networks using gait descriptors directly. Results: the accuracy of the 3D camera to objectify human gait was measured before and after training. In both training approaches, a considerable improvement was observed. Kinematic gait signals showed lower errors and higher correlations with respect to the ground truth. The accuracy of the system to detect gait descriptors also showed a substantial improvement, mostly for kinematic descriptors rather than spatio-temporal. When comparing both training approaches, it was not possible to define which was the absolute best. Conclusions: supervised learning improves the accuracy of 3D cameras but the selection of the training approach will depend on the purpose of the study to be conducted. This study reveals the great potential of 3D cameras and encourages the research community to continue exploring their use in gait analysis.
Some of the metrics are blocked by your
consent settings
Robotics‐driven gait analysis: Assessing Azure Kinect's performance in in‐lab versus in‐corridor environments
(Wiley, 2024-03-13)
GUFFANTI MARTINEZ, DIEGO ANDRES
;
Alberto Brunete
;
Miguel Hernando
;
David Álvarez
;
Ernesto Gambao
Abstract Gait analysis offers vital insights into human movement, aiding in the diagnosis, treatment, and rehabilitation of various conditions. Analyzing gait in corridors, rather than in lab, provides unique advantages for a more comprehensive understanding of human locomotion. However, limited dedicated technologies constrain gait data analysis in this context. In this study, a markerless gait analysis system using an Azure Kinect sensor mounted on a mobile robot is proposed and validated as a potential solution for gait analysis in corridors. Ten healthy participants (4 males and 6 females) underwent two tests. The first test (5 trials per participant) took place in the laboratory. Here, Azure Kinect performance was validated against a Vicon system, assessing eight gait signals and 22 gait parameters. The second test (2 trials per participant) was performed in the corridors over a 32‐m walking distance to compare this gait pattern with the one developed within the laboratory. The intrasession Intraclass Correlation Coefficient (ICC) reliability for in‐lab experiments was assessed by calculating the ICC between gait cycles captured in each session per participant. Notably, knee flexion/extension (ICC‐0.95), hip flexion/extension (ICC‐0.96), pelvis rotation (ICC‐0.88), and interankle distance (ICC‐0.98) demonstrated excellent reliability with high confidence. Similarly, hip adduction/abduction showed good reliability (ICC‐0.79), while trunk rotation exhibited moderate reliability (ICC‐0.72). In contrast, both trunk tilt (ICC‐0.24) and pelvis tilt (ICC‐0.41) consistently displayed lower reliability. This was observed for both the Vicon and the Azure systems, highlighting the intricate nature of capturing precise data for these specific signals in both systems. Validity outcomes indicated comparable error rates to literature standards ( knee flexion/extension, hip flexion/extension, and hip adduction/abduction), with 11 parameters having no significant differences from Vicon. Comparison of in‐lab and in‐corridor experiments show that individuals exhibit significantly longer stride time (1.10 s vs. 1.05 s), lower pelvis tilt ( vs. ), and lower minimum pelvis rotation ( vs. ) when walking in the laboratory. This study demonstrates promising outcomes in outdoor gait analysis with a robot‐mounted camera, revealing significant distinctions from controlled laboratory evaluations.

CRIS

Browse

Filters

Settings

Sort By

Results per page

Search Results