The Experts below are selected from a list of 810 Experts worldwide ranked by ideXlab platform
Petros Maragos - One of the best experts on this subject based on the ideXlab platform.
-
The i-Walk Lightweight Assistive Rollator: First Evaluation Study
'Frontiers Media SA', 2021Co-Authors: George Moustris, Georgia Chalvatzaki, Petros Koutras, Costas S Tzafestas, Petros Maragos, Nikolaos Kardaris, Antigoni Tsiami, Athanasios Dometios, Paris Oikonomou, Eleni EfthimiouAbstract:Robots can play a significant role as assistive devices for people with movement impairment and mild cognitive deficit. In this paper we present an overview of the lightweight i-Walk intelligent robotic Rollator, which offers cognitive and mobility assistance to the elderly and to people with light to moderate mobility impairment. The utility, usability, safety and technical performance of the device is investigated through a clinical study, which took place at a rehabilitation center in Greece involving real patients with mild to moderate cognitive and mobility impairment. This first evaluation study comprised a set of scenarios in a number of pre-defined use cases, including physical rehabilitation exercises, as well as mobility and ambulation involved in typical daily living activities of the patients. The design and implementation of this study is discussed in detail, along with the obtained results, which include both an objective and a subjective evaluation of the system operation, based on a set of technical performance measures and a validated questionnaire for the analysis of qualitative data, respectively. The study shows that the technical modules performed satisfactory under real conditions, and that the users generally hold very positive views of the platform, considering it safe and reliable
-
lstm based network for human gait stability prediction in an intelligent robotic Rollator
International Conference on Robotics and Automation, 2019Co-Authors: Georgia Chalvatzaki, Petros Koutras, Jack Hadfield, Xanthi S Papageorgiou, Costas S Tzafestas, Petros MaragosAbstract:In this work, we present a novel framework for on-line human gait stability prediction of the elderly users of an intelligent robotic Rollator using Long Short Term Memory (LSTM) networks, fusing multimodal RGB-D and Laser Range Finder (LRF) data from non-wearable sensors. A Deep Learning (DL) based approach is used for the upper body pose estimation. The detected pose is used for estimating the body Center of Mass (CoM) using Unscented Kalman Filter (UKF). An Augmented Gait State Estimation framework exploits the LRF data to estimate the legs’ positions and the respective gait phase. These estimates are the inputs of an encoder-decoder sequence to sequence model which predicts the gait stability state as Safe or Fall Risk walking. It is validated with data from real patients, by exploring different network architectures, hyperparameter settings and by comparing the proposed method with other baselines. The presented LSTM-based human gait stability predictor is shown to provide robust predictions of the human stability state, and thus has the potential to be integrated into a general user-adaptive control architecture as a fall-risk alarm.
Joaquin Ballesteros - One of the best experts on this subject based on the ideXlab platform.
-
A Biomimetical Dynamic Window Approach to Navigation for Collaborative Control
IEEE Transactions on Human-Machine Systems, 2017Co-Authors: Joaquin Ballesteros, Cristina Urdiales, Antonio Martínez B. Velasco, Gonzalo Ramos-jiménezAbstract:Shared control is a strategy used in assistive platforms to combine human and robot orders to achieve a goal. Collaborative control is a specific shared control approach, in which user's and robot's commands are merged into an emergent one in a continuous way. Robot commands tend to improve efficiency and safety. However, sometimes, assistance can be rejected by users when their commands are too altered. This provokes frustration and stress and, usually, decreases emergent efficiency. To improve acceptance, robot navigation algorithms can be adapted to mimic human behavior when possible. We propose a novel variation of the well-known dynamic window approach (DWA) that we call biomimetical DWA (BDWA). The BDWA relies on a reward function extracted from real traces from volunteers presenting different motor disabilities navigating in a hospital environment using a Rollator for support. We have compared the BDWA with other reactive algorithms in terms of similarity to paths completed by people with disabilities using a robotic Rollator in a rehabilitation hospital unit. The BDWA outperforms all tested algorithms in terms of likeness to human paths and success rate.
-
On Gait Analysis Estimation Errors Using Force Sensors on a Smart Rollator
MDPI AG, 2016Co-Authors: Joaquin Ballesteros, Cristina Urdiales, Antonio B. Martinez, Jaap H. Van DieënAbstract:Gait analysis can provide valuable information on a person’s condition and rehabilitation progress. Gait is typically captured using external equipment and/or wearable sensors. These tests are largely constrained to specific controlled environments. In addition, gait analysis often requires experts for calibration, operation and/or to place sensors on volunteers. Alternatively, mobility support devices like Rollators can be equipped with onboard sensors to monitor gait parameters, while users perform their Activities of Daily Living. Gait analysis in Rollators may use odometry and force sensors in the handlebars. However, force based estimation of gait parameters is less accurate than traditional methods, especially when Rollators are not properly used. This paper presents an evaluation of force based gait analysis using a smart Rollator on different groups of users to determine when this methodology is applicable. In a second stage, the Rollator is used in combination with two lab-based gait analysis systems to assess the Rollator estimation error. Our results show that: (i) there is an inverse relation between the variance in the force difference between handlebars and support on the handlebars—related to the user condition—and the estimation error; and (ii) this error is lower than 10% when the variation in the force difference is above 7 N. This lower limit was exceeded by the 95.83% of our challenged volunteers. In conclusion, Rollators are useful for gait characterization as long as users really need the device for ambulation
Georgia Chalvatzaki - One of the best experts on this subject based on the ideXlab platform.
-
The i-Walk Lightweight Assistive Rollator: First Evaluation Study
'Frontiers Media SA', 2021Co-Authors: George Moustris, Georgia Chalvatzaki, Petros Koutras, Costas S Tzafestas, Petros Maragos, Nikolaos Kardaris, Antigoni Tsiami, Athanasios Dometios, Paris Oikonomou, Eleni EfthimiouAbstract:Robots can play a significant role as assistive devices for people with movement impairment and mild cognitive deficit. In this paper we present an overview of the lightweight i-Walk intelligent robotic Rollator, which offers cognitive and mobility assistance to the elderly and to people with light to moderate mobility impairment. The utility, usability, safety and technical performance of the device is investigated through a clinical study, which took place at a rehabilitation center in Greece involving real patients with mild to moderate cognitive and mobility impairment. This first evaluation study comprised a set of scenarios in a number of pre-defined use cases, including physical rehabilitation exercises, as well as mobility and ambulation involved in typical daily living activities of the patients. The design and implementation of this study is discussed in detail, along with the obtained results, which include both an objective and a subjective evaluation of the system operation, based on a set of technical performance measures and a validated questionnaire for the analysis of qualitative data, respectively. The study shows that the technical modules performed satisfactory under real conditions, and that the users generally hold very positive views of the platform, considering it safe and reliable
-
lstm based network for human gait stability prediction in an intelligent robotic Rollator
International Conference on Robotics and Automation, 2019Co-Authors: Georgia Chalvatzaki, Petros Koutras, Jack Hadfield, Xanthi S Papageorgiou, Costas S Tzafestas, Petros MaragosAbstract:In this work, we present a novel framework for on-line human gait stability prediction of the elderly users of an intelligent robotic Rollator using Long Short Term Memory (LSTM) networks, fusing multimodal RGB-D and Laser Range Finder (LRF) data from non-wearable sensors. A Deep Learning (DL) based approach is used for the upper body pose estimation. The detected pose is used for estimating the body Center of Mass (CoM) using Unscented Kalman Filter (UKF). An Augmented Gait State Estimation framework exploits the LRF data to estimate the legs’ positions and the respective gait phase. These estimates are the inputs of an encoder-decoder sequence to sequence model which predicts the gait stability state as Safe or Fall Risk walking. It is validated with data from real patients, by exploring different network architectures, hyperparameter settings and by comparing the proposed method with other baselines. The presented LSTM-based human gait stability predictor is shown to provide robust predictions of the human stability state, and thus has the potential to be integrated into a general user-adaptive control architecture as a fall-risk alarm.
Hauer Klaus - One of the best experts on this subject based on the ideXlab platform.
-
Concurrent Validity, Test-Retest Reliability, and Sensitivity to Change of a Single Body-Fixed Sensor for Gait Analysis during Rollator-Assisted Walking in Acute Geriatric Patients
MDPI, 2020Co-Authors: Werner Christian, Heldmann Patrick, Hummel Saskia, Bauknecht Laura, Bauer, Jürgen M., Hauer KlausAbstract:Body-fixed sensor (BFS) technology offers portable, low-cost and easy-to-use alternatives to laboratory-bound equipment for analyzing an individual's gait. Psychometric properties of single BFS systems for gait analysis in older adults who require a Rollator for walking are, however, unknown. The study's aim was to evaluate the concurrent validity, test-retest-reliability, and sensitivity to change of a BFS (DynaPort MoveTest; McRoberts B.V., The Hague, The Netherlands) for measuring gait parameters during Rollator-assisted walking. Fifty-eight acutely hospitalized older patients equipped with the BFS at the lower back completed a 10 m walkway using a Rollator. Concurrent validity was assessed against the Mobility Lab (APDM Inc.; Portland, OR, USA), test-retest reliability over two trials within a 15 min period, and sensitivity to change in patients with improved, stable and worsened 4 m usual gait speed over hospital stay. Bland-Altman plots and intraclass correlation coefficients (ICC) for gait speed, cadence, step length, step time, and walk ratio indicate good to excellent agreement between the BFS and the Mobility Lab (ICC2,1 = 0.87-0.99) and the repeated trials (ICC2,1 = 0.83-0.92). Moderate to large standardized response means were observed in improved (gait speed, cadence, step length, walk ratio: 0.62-0.99) and worsened patients (gait speed, cadence, step time: -0.52 to -0.85), while those in stable patients were trivial to small (all gait parameters: -0.04-0.40). The BFS appears to be a valid, reliable and sensitive instrument for measuring spatio-temporal gait parameters during Rollator-assisted walking in geriatric patients
-
An Integrated Decision Making Approach for Adaptive Shared Control of Mobility Assistance Robots
'Springer Science and Business Media LLC', 2016Co-Authors: Geravand Milad, Hauer Klaus, Werner Christian, Peer AngelikaAbstract:© 2016, Springer Science+Business Media Dordrecht. Mobility assistance robots provide support to elderly or patients during walking. The design of a safe and intuitive assistance behavior is one of the major challenges in this context. We present an integrated approach for the context-specific, on-line adaptation of the assistance level of a Rollator-type mobility assistance robot by gain-scheduling of low-level robot control parameters. A human-inspired decision-making model, the drift-diffusion Model, is introduced as the key principle to gain-schedule parameters and with this to adapt the provided robot assistance in order to achieve a human-like assistive behavior. The mobility assistance robot is designed to provide (a) cognitive assistance to help the user following a desired path towards a predefined destination as well as (b) sensorial assistance to avoid collisions with obstacles while allowing for an intentional approach of them. Further, the robot observes the user long-term performance and fatigue to adapt the overall level of (c) physical assistance provided. For each type of assistance a decision-making problem is formulated that affects different low-level control parameters. The effectiveness of the proposed approach is demonstrated in technical validation experiments. Moreover, the proposed approach is evaluated in a user study with 35 elderly persons. Obtained results indicate that the proposed gain-scheduling technique incorporating ideas of human decision-making models shows a general high potential for the application in adaptive shared control of mobility assistance robots
-
Rollator use adversely impacts on assessment of gait and mobility during geriatric rehabilitation
'Acta Dermato-Venereologica', 2011Co-Authors: Schwenk Michael, Schmidt Marita, Pfisterer Matthias, Oster Peter, Hauer KlausAbstract:Objective: To investigate the influence of the use of a Rollator walking aid on assessment of gait and mobility. Design: Prospective, longitudinal study. Subjects: Geriatric patients during inpatient rehabilitation (n = 109; mean age 83.1 years). Methods: Assessment at the beginning and prior to discharge from rehabilitation using: gait-analysis (GAITRite®, speed, cadence, stride-time, stride-length, base-of-support, double-support), Performance-Oriented-Mobility-Assessment (POMA), and Timed-Up-and-Go (TUG). Differences between outcomes obtained without and with Rollator use were calculated for baseline assessment and for changes over time for the total group and subgroups according to diagnosis (hip fracture vs. other). Responsiveness was calculated using standardized response means. Results: Baseline performances were significantly (p ≤ 0.05) higher when assessed with vs. without Rollator in the total group and in hip fracture (except cadence) and other (except cadence, stride-time, TUG) patients. Changes over time were significantly greater when assessed without vs. with Rollator in the total group and hip fracture (except cadence, POMA) and other patients (except base-of-support, double-support). Tests without Rollator showed superior responsiveness (except TUG). Conclusion: The use of Rollator walking aids limits the detection of initial gait and mobility deficits, adversely affects the assessment of changes over time in gait and mobility performance, and reduces the responsiveness of tests. When full weight-bearing is permitted, assessment without a walking aid is recommended.publishe
Catherine Holloway - One of the best experts on this subject based on the ideXlab platform.
-
Rollator movement IMU data - gold standard
2016Co-Authors: Tsu-jui Cheng, Laurence Kenney, James D. Amor, Sibylle Brunhilde Anitha Thies, Eleonora Costamagna, Christopher J. James, Catherine HollowayAbstract:This is an initial study to characterise Rollator movement. An inertial measurement unit (IMU) was used to measure the motion of the Rollator and analytical approaches were developed to extract features characterising the Rollator movement, properties of the surface, and push events. The analytics were tested in two situations, firstly a healthy participant used a Rollator in a laboratory using a motion capture system to obtain ground truth. Secondly the IMU was used to measure the movement of a Rollator being used by a user with multiple sclerosis (MS) on a flat surface, cross-slope, up and down slopes, and up and down a step The dataset of inertial measurement unit is comprised of seven straight-lighting walking trials (between 4-5 m) performed by a healthy participant using a Rollator in a gait lab. The raw data were in txt format recorded by Xsens Swinda 2 and subsequently analysed using a bespoke MATLAB script to calculate the distance travelled by a Rollator
-
Rollator movement motion sensing data - gold standard
2016Co-Authors: Tsu-jui Cheng, Laurence Kenney, James D. Amor, Sibylle Brunhilde Anitha Thies, Eleonora Costamagna, Christopher J. James, Catherine HollowayAbstract:This is an initial study to characterise Rollator movement. An inertial measurement unit (IMU) was used to measure the motion of the Rollator and analytical approaches were developed to extract features characterising the Rollator movement, properties of the surface, and push events. The analytics were tested in two situations, firstly a healthy participant used a Rollator in a laboratory using a motion capture system to obtain ground truth. Secondly the IMU was used to measure the movement of a Rollator being used by a user with multiple sclerosis (MS) on a flat surface, cross-slope, up and down slopes, and up and down a step The dataset of motion sensing movement is comprised of seven straight-lighting walking trials (between 4-5 m) performed by a healthy participant using a Rollator in a gait lab. The raw data were in csv format recorded by VICON system and subsequently analysed in Microsoft Excel 2013 to calculate the distance travelled by a Rollator
-
Rollator movement IMU data - simulated urban environment
2016Co-Authors: Tsu-jui Cheng, Laurence Kenney, James D. Amor, Sibylle Brunhilde Anitha Thies, Eleonora Costamagna, Christopher J. James, Catherine HollowayAbstract:This is an initial study to characterise Rollator movement. An inertial measurement unit (IMU) was used to measure the motion of the Rollator and analytical approaches were developed to extract features characterising the Rollator movement, properties of the surface, and push events. The analytics were tested in two situations, firstly a healthy participant used a Rollator in a laboratory using a motion capture system to obtain ground truth. Secondly the IMU was used to measure the movement of a Rollator being used by a user with multiple sclerosis (MS) on a flat surface, cross-slope, up and down slopes, and up and down a step The dataset of inertial measurement unit is comprised of two straight-lighting walking trials (file 000 and 001), three trials on a 4% crossslope (file 003-005), four trials on a 6% ramp (file 006-009) and four trials over a 80mm step (file 010-013) performed by an multiple sclerosis participant using a Rollator in an simulated urban environment in a lab. The raw data were in txt format recorded by Xsens Swinda and subsequently analysed using a bespoke MATLAB script to calculate the distance travelled and property surfaces
-
Calculation of distance travelled and surface properties - MATLAB script
2016Co-Authors: Tsu-jui Cheng, Laurence Kenney, James D. Amor, Sibylle Brunhilde Anitha Thies, Eleonora Costamagna, Christopher J. James, Catherine HollowayAbstract:This is an initial study to characterise Rollator movement. An inertial measurement unit (IMU) was used to measure the motion of the Rollator and analytical approaches were developed to extract features characterising the Rollator movement, properties of the surface, and push events. The analytics were tested in two situations, firstly a healthy participant used a Rollator in a laboratory using a motion capture system to obtain ground truth. Secondly the IMU was used to measure the movement of a Rollator being used by a user with multiple sclerosis (MS) on a flat surface, cross-slope, up and down slopes, and up and down a step.Unzip the entire folder and run calcDistance.m and it will load the IMU data from the Xsens_Rollator folder and then create fig files in the OutputFigs folder. There are also variables in this zip file that contain output data (meanPushDist and totalPushes) which show average push distance and total number of pushes for each trial.