Xiaowei Tan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Xiaowei Tan has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Bi Zhang
State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
9 shared publications - Xingang Zhao
Chinese Academy of Sciences
9 shared publications Yiwen Zhao
Shenyang Institute of Automation, State Key Laboratory of Robotics and Intelligent Systems, Chinese Academy of Sciences, Shenyang, China
5 shared publications- Guangjun Liu
Department of Aerospace Engineering, Toronto Metropolitan University, Toronto, ON M5B 2K3, Canada
3 shared publications - Lianqing Liu
Chinese Academy of Sciences
3 shared publications - Wanxin Chen
State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
3 shared publications
Latest Publications
- 3 May 2026
- Published by SAGE Publications in The International Journal of Robotics Research
K2MUSE: A human lower-limb multimodal walking dataset spanning task and acquisition variability for rehabilitation robotics
The natural interaction and control performance of lower limb rehabilitation robots are closely linked to biomechanical information from various human locomotion activities. Multidimensional human motion data significantly deepen the understanding of the complex mechanisms governing neuromuscular alterations, thereby facilitating the development and application of rehabilitation robots in multifaceted real-world environments. However, existing lower limb datasets are inadequate for supplying the essential multimodal data and large-scale gait samples necessary for the development of effective data-driven approaches, and the significant effects of acquisition interference in real applications are neglected. To fill this gap, we present the K2MUSE dataset, which includes a comprehensive collection of multimodal data, comprising kinematic, kinetic, amplitude mode ultrasound (AUS), and surface electromyography (sEMG) measurements. The proposed dataset includes lower limb multimodal data collected from two cohorts, including 30 able-bodied young adults and 12 older adults, across different inclines (0°, ±5°, and ±10°), speeds (0.5 m/s, 1.0 m/s, and 1.5 m/s), and representative non-ideal acquisition conditions (muscle fatigue, electrode shifts, and interday differences). The kinematic and ground reaction force data were collected with a Vicon motion capture system and an instrumented treadmill with embedded force plates, whereas the sEMG and AUS data of 13 muscles on the bilateral lower limbs were synchronously recorded. To validate the quality of the data, we quantified repeatability across locomotion modes, speeds, and inclines, examined physiological signatures under non-ideal acquisition conditions, and observed high agreement with existing public datasets. We also report baseline motion-intention recognition results, including joint angle estimation and gait phase classification, with a multimodal transformer model demonstrating accurate and stable performance. In addition, we present a control-oriented application in which an end-to-end model trained on the K2MUSE dataset provides hip assistance via a soft exoskeleton and yields consistent reductions in metabolic cost across multiple terrains. K2MUSE is released with the corresponding structured documentation, preprocessing pipelines, and example code, thereby providing a comprehensive resource for rehabilitation robot development, biomechanical analysis, and wearable sensing research. The dataset is available at https://k2muse.github.io/ .
- 3 May 2026
- Published by SAGE Publications in The International Journal of Robotics Research
K2MUSE: A human lower-limb multimodal walking dataset spanning task and acquisition variability for rehabilitation robotics
The natural interaction and control performance of lower limb rehabilitation robots are closely linked to biomechanical information from various human locomotion activities. Multidimensional human motion data significantly deepen the understanding of the complex mechanisms governing neuromuscular alterations, thereby facilitating the development and application of rehabilitation robots in multifaceted real-world environments. However, existing lower limb datasets are inadequate for supplying the essential multimodal data and large-scale gait samples necessary for the development of effective data-driven approaches, and the significant effects of acquisition interference in real applications are neglected. To fill this gap, we present the K2MUSE dataset, which includes a comprehensive collection of multimodal data, comprising kinematic, kinetic, amplitude mode ultrasound (AUS), and surface electromyography (sEMG) measurements. The proposed dataset includes lower limb multimodal data collected from two cohorts, including 30 able-bodied young adults and 12 older adults, across different inclines (0°, ±5°, and ±10°), speeds (0.5 m/s, 1.0 m/s, and 1.5 m/s), and representative non-ideal acquisition conditions (muscle fatigue, electrode shifts, and interday differences). The kinematic and ground reaction force data were collected with a Vicon motion capture system and an instrumented treadmill with embedded force plates, whereas the sEMG and AUS data of 13 muscles on the bilateral lower limbs were synchronously recorded. To validate the quality of the data, we quantified repeatability across locomotion modes, speeds, and inclines, examined physiological signatures under non-ideal acquisition conditions, and observed high agreement with existing public datasets. We also report baseline motion-intention recognition results, including joint angle estimation and gait phase classification, with a multimodal transformer model demonstrating accurate and stable performance. In addition, we present a control-oriented application in which an end-to-end model trained on the K2MUSE dataset provides hip assistance via a soft exoskeleton and yields consistent reductions in metabolic cost across multiple terrains. K2MUSE is released with the corresponding structured documentation, preprocessing pipelines, and example code, thereby providing a comprehensive resource for rehabilitation robot development, biomechanical analysis, and wearable sensing research. The dataset is available at https://k2muse.github.io/ .
- 10 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 13 (2) , 259-280
A Systematic Review of Respiratory Monitoring and Assistance Techniques from a Pulmonary Rehabilitation Robot Perspective
Pulmonary rehabilitation (PR) aims to improve lung function in patients with chronic respiratory disease (CRD). In recent years, significant advancements have been made in pulmonary rehabilitation technologies, demonstrating their potential for enhancing lung function in patients with respiratory diseases. The purpose of this study is to outline recent developments in the field of pulmonary rehabilitation guided by pulmonary rehabilitation robots, which has not been previously addressed in earlier reviews. To fill this gap, this paper first provides a systematic summary of the monitoring and actuation technologies of pulmonary rehabilitation robot systems and evaluates these technologies from multiple dimensions, including portability, wearability potential, invasiveness, and clinical applications, analyzing the potential for integrating various technologies into pulmonary rehabilitation robot systems. Furthermore, three technical directions are proposed: real-time precise monitoring, suitable structure and actuation strategies, and the intelligence of pulmonary rehabilitation robot systems. On the basis of these directions, this paper presents a comprehensive technical outlook for a soft wearable pulmonary rehabilitation robot system, providing reference and guidance for future research. To our knowledge, this is the first review of pulmonary rehabilitation robot systems and their key technologies. Additionally, the review section on respiratory assistive technologies simultaneously covers key technologies such as mechanical ventilation (MV), exoskeleton robots, and functional electrical stimulation (FES) for the first time. It also summarizes the respiratory assistive technology paradigm from the innovative perspectives of respiratory assistive modalities, targeted body sites, and types of ventilation for the first time. This study offers a broader perspective and a deeper understanding of pulmonary re-habilitation robots, with a technical outlook encompassing multimodal data fusion perception, respiratory event detection and intention recognition, full-phase assistance strategies, modeling, decoupling, and quantification of multiple-input multiple-output (MIMO) systems, as well as model-based interactive control strategies.
- 10 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/CAA Journal of Automatica Sinica
- Vol. 13 (2) , 259-280
A Systematic Review of Respiratory Monitoring and Assistance Techniques from a Pulmonary Rehabilitation Robot Perspective
Pulmonary rehabilitation (PR) aims to improve lung function in patients with chronic respiratory disease (CRD). In recent years, significant advancements have been made in pulmonary rehabilitation technologies, demonstrating their potential for enhancing lung function in patients with respiratory diseases. The purpose of this study is to outline recent developments in the field of pulmonary rehabilitation guided by pulmonary rehabilitation robots, which has not been previously addressed in earlier reviews. To fill this gap, this paper first provides a systematic summary of the monitoring and actuation technologies of pulmonary rehabilitation robot systems and evaluates these technologies from multiple dimensions, including portability, wearability potential, invasiveness, and clinical applications, analyzing the potential for integrating various technologies into pulmonary rehabilitation robot systems. Furthermore, three technical directions are proposed: real-time precise monitoring, suitable structure and actuation strategies, and the intelligence of pulmonary rehabilitation robot systems. On the basis of these directions, this paper presents a comprehensive technical outlook for a soft wearable pulmonary rehabilitation robot system, providing reference and guidance for future research. To our knowledge, this is the first review of pulmonary rehabilitation robot systems and their key technologies. Additionally, the review section on respiratory assistive technologies simultaneously covers key technologies such as mechanical ventilation (MV), exoskeleton robots, and functional electrical stimulation (FES) for the first time. It also summarizes the respiratory assistive technology paradigm from the innovative perspectives of respiratory assistive modalities, targeted body sites, and types of ventilation for the first time. This study offers a broader perspective and a deeper understanding of pulmonary re-habilitation robots, with a technical outlook encompassing multimodal data fusion perception, respiratory event detection and intention recognition, full-phase assistance strategies, modeling, decoupling, and quantification of multiple-input multiple-output (MIMO) systems, as well as model-based interactive control strategies.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-17
Robust Real-Time Gait Event Detection Across Diverse Activities Using a Single IMU
Gait events are critical for both clinical analysis and the real-time control of robotic systems. However, existing detec-tion systems often exhibit limited robustness across different lo-comotion activities and conditions. Achieving a balance among real-time performance, low complexity, adaptability, and outdoor robustness remains a major challenge. This work presents a sin-gle-IMU-based gait event detection system capable of accurately identifying foot contact (FC), foot-off (FO), static foot, and dy-namic foot events in real time across eight locomotion activities and thirty-eight conditions. This system associates gait events with two fundamental types of features, namely, static foot states and peak points on foot motion profiles. These features are inherently present across different gaits and activities due to the alternating motion of the legs and the periodic nature of gait. Two adaptive threshold-based methods were developed to capture these features reliably. Experiments were conducted with eleven subjects, each completing twenty-one trials covering eight activity types and thirty-eight conditions. A total of 36,055 valid FC events and 36,125 valid FO events were recorded, yielding an average detec-tion accuracy of 99.54% and a detection delay of -41.3 ms, which indicates that the events were detected earlier than the ground-truth references. Moreover, an outdoor case study con-firmed the system’s robustness under challenging environmental conditions. Finally, potential applications in home-based gait evaluation and exoskeleton control are discussed, highlighting the promising prospects of the proposed system.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-17
Robust Real-Time Gait Event Detection Across Diverse Activities Using a Single IMU
Gait events are critical for both clinical analysis and the real-time control of robotic systems. However, existing detec-tion systems often exhibit limited robustness across different lo-comotion activities and conditions. Achieving a balance among real-time performance, low complexity, adaptability, and outdoor robustness remains a major challenge. This work presents a sin-gle-IMU-based gait event detection system capable of accurately identifying foot contact (FC), foot-off (FO), static foot, and dy-namic foot events in real time across eight locomotion activities and thirty-eight conditions. This system associates gait events with two fundamental types of features, namely, static foot states and peak points on foot motion profiles. These features are inherently present across different gaits and activities due to the alternating motion of the legs and the periodic nature of gait. Two adaptive threshold-based methods were developed to capture these features reliably. Experiments were conducted with eleven subjects, each completing twenty-one trials covering eight activity types and thirty-eight conditions. A total of 36,055 valid FC events and 36,125 valid FO events were recorded, yielding an average detec-tion accuracy of 99.54% and a detection delay of -41.3 ms, which indicates that the events were detected earlier than the ground-truth references. Moreover, an outdoor case study con-firmed the system’s robustness under challenging environmental conditions. Finally, potential applications in home-based gait evaluation and exoskeleton control are discussed, highlighting the promising prospects of the proposed system.
- 8 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. PP (15455955) , 1
Modular Soft Exoskeleton Design and Control for Assisting Movements in Multiple Lower Limb Joint Configurations
Soft lower limb exoskeletons have shown potential to enhance mobility in patients with motor disorders and improve their quality of life. This study introduces a novel modular soft lower-limb exoskeleton that provides assistance to a single hip joint or/and a single ankle joint, configurable on either the left or right side according to clinical needs. The control system employs adaptive gait phase recognition and a hierarchical strategy to accurately identify user intentions and track desired assistance profiles. An assistance profile optimization method is also designed based on the users’ muscle surface electromyography signals, aiming to further enhance the adaptability of robotic assistance to different users and tasks. Multi-subject experiments were conducted with 10 participants. The experimental results demonstrated that the exoskeleton exhibited good modular performance and effectively assisted walking under different configurations. Specifically, compared to natural walking, the exoskeleton assistance reduced the net metabolic rate by up to 15.29% while the hip and ankle joints are assisted simultaneously. Furthermore, the optimized assistance profiles achieved lower metabolic rates and reduced muscle activation compared to the generic assistance.
- 8 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. PP (15455955) , 1
Modular Soft Exoskeleton Design and Control for Assisting Movements in Multiple Lower Limb Joint Configurations
Soft lower limb exoskeletons have shown potential to enhance mobility in patients with motor disorders and improve their quality of life. This study introduces a novel modular soft lower-limb exoskeleton that provides assistance to a single hip joint or/and a single ankle joint, configurable on either the left or right side according to clinical needs. The control system employs adaptive gait phase recognition and a hierarchical strategy to accurately identify user intentions and track desired assistance profiles. An assistance profile optimization method is also designed based on the users’ muscle surface electromyography signals, aiming to further enhance the adaptability of robotic assistance to different users and tasks. Multi-subject experiments were conducted with 10 participants. The experimental results demonstrated that the exoskeleton exhibited good modular performance and effectively assisted walking under different configurations. Specifically, compared to natural walking, the exoskeleton assistance reduced the net metabolic rate by up to 15.29% while the hip and ankle joints are assisted simultaneously. Furthermore, the optimized assistance profiles achieved lower metabolic rates and reduced muscle activation compared to the generic assistance.
- 19 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 41 (15523098) , 269-288
Hip–Knee–Ankle Rehabilitation Exoskeleton With Compliant Actuators: From Human–Robot Interaction Control to Clinical Evaluation
While rehabilitation exoskeletons have been extensively studied, systematic design principles for effectively addressing heterogeneous bilateral locomotion in hemiplegia patients are poorly understood. In this article, a multijoint lower exoskeleton driven by series elastic actuators (SEAs) is developed, and the design philosophy of rehabilitation robots for hemiplegia patients is systematically explored. The exoskeleton has six powered joints for both lower limbs in a hip–knee–ankle configuration, and each joint incorporates a custom, lightweight SEA module. A unified interaction-oriented control framework is designed for exoskeleton-assisted walking, including gait generation, task scheduling, and advanced joint-level control. The closed-loop design provides methodical solutions to address hemiplegia rehabilitation needs and provides walking assistance for bilateral lower limbs. Moreover, a multitemplate gait generation approach is proposed to address the altered kinematics induced by exoskeleton-assisted walking and enhance the exoskeleton's adaptability to patient-specific kinematic variations in an iterative manner. Experiments are conducted with both healthy individuals and hemiplegia patients to verify the effectiveness of the exoskeleton system. The clinical outcomes demonstrate that the exoskeleton can achieve mechanical transparency, facilitate movement, and enable coordinated interjoint locomotion for bilateral gait assistance.
- 19 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 41 (15523098) , 269-288
Hip–Knee–Ankle Rehabilitation Exoskeleton With Compliant Actuators: From Human–Robot Interaction Control to Clinical Evaluation
While rehabilitation exoskeletons have been extensively studied, systematic design principles for effectively addressing heterogeneous bilateral locomotion in hemiplegia patients are poorly understood. In this article, a multijoint lower exoskeleton driven by series elastic actuators (SEAs) is developed, and the design philosophy of rehabilitation robots for hemiplegia patients is systematically explored. The exoskeleton has six powered joints for both lower limbs in a hip–knee–ankle configuration, and each joint incorporates a custom, lightweight SEA module. A unified interaction-oriented control framework is designed for exoskeleton-assisted walking, including gait generation, task scheduling, and advanced joint-level control. The closed-loop design provides methodical solutions to address hemiplegia rehabilitation needs and provides walking assistance for bilateral lower limbs. Moreover, a multitemplate gait generation approach is proposed to address the altered kinematics induced by exoskeleton-assisted walking and enhance the exoskeleton's adaptability to patient-specific kinematic variations in an iterative manner. Experiments are conducted with both healthy individuals and hemiplegia patients to verify the effectiveness of the exoskeleton system. The clinical outcomes demonstrate that the exoskeleton can achieve mechanical transparency, facilitate movement, and enable coordinated interjoint locomotion for bilateral gait assistance.
- Open Access
- 15 February 2023
- Published by Elsevier in Brain Stimulation
- Vol. 16 (1) , 393
Effect of early electroconvulsive therapy on length of stay in patients with bipolar, depressive and psychotic disorders
- 15 February 2023
- Published by Elsevier in Brain Stimulation
- Vol. 16 (1) , 393
Open AccessEffect of early electroconvulsive therapy on length of stay in patients with bipolar, depressive and psychotic disorders
- Open Access
- 15 February 2023
- Published by Elsevier in Brain Stimulation
- Vol. 16 (1) , 229
The effect of Outpatient Continuation Electroconvulsive Therapy (C-ECT) on the Readmission Risk and Total Direct Cost in Patients with Depressive, Bipolar and Psychotic Disorders: A Naturalistic Retrospective Cohort Study
- 15 February 2023
- Published by Elsevier in Brain Stimulation
- Vol. 16 (1) , 229
Open AccessThe effect of Outpatient Continuation Electroconvulsive Therapy (C-ECT) on the Readmission Risk and Total Direct Cost in Patients with Depressive, Bipolar and Psychotic Disorders: A Naturalistic Retrospective Cohort Study
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 39 (2) , 1653-1667
A Time-Independent Control System for Natural Human Gait Assistance With a Soft Exoskeleton
When applying exoskeletons for walking assistance, one important consideration is to ensure that the users retain full control over the exoskeleton-provided assistance, which is quite limited in existing exoskeletons due to the absence of a suitable control system. In this article, a time-independent exoskeleton control system is developed based on a novel assistance profile generation method and an iterative force control method to enable continuous assistance adjustment. The assistance profile is formulated as a Gaussian function with a human state variable and can be updated online to adapt to different users. The proposed profile continuously self-adjusts along the movement of the user's leg, especially when users change their walking patterns. The proposed control system iteratively compensates for the force control lag and amplitude attenuation to enable precise tracking of the assistance profile during natural human walking. Experiments have been conducted using a soft exoskeleton on subjects with and without prior experience using an exoskeleton. The experimental results have shown the effectiveness of the proposed control system compared with a common time-dependent control system.
- 22 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Robotics
- Vol. 39 (2) , 1653-1667
A Time-Independent Control System for Natural Human Gait Assistance With a Soft Exoskeleton
When applying exoskeletons for walking assistance, one important consideration is to ensure that the users retain full control over the exoskeleton-provided assistance, which is quite limited in existing exoskeletons due to the absence of a suitable control system. In this article, a time-independent exoskeleton control system is developed based on a novel assistance profile generation method and an iterative force control method to enable continuous assistance adjustment. The assistance profile is formulated as a Gaussian function with a human state variable and can be updated online to adapt to different users. The proposed profile continuously self-adjusts along the movement of the user's leg, especially when users change their walking patterns. The proposed control system iteratively compensates for the force control lag and amplitude attenuation to enable precise tracking of the assistance profile during natural human walking. Experiments have been conducted using a soft exoskeleton on subjects with and without prior experience using an exoskeleton. The experimental results have shown the effectiveness of the proposed control system compared with a common time-dependent control system.
- 13 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 51 (6) , 684-695
Phase Variable Based Recognition of Human Locomotor Activities Across Diverse Gait Patterns
Human locomotor activity (LA) recognition is important in the control of exoskeletons and prostheses and in patient monitoring. This article presents a practical recognition approach that can classify level walking, stair ascent, and stair descent activities across different subjects and diverse gait patterns. The thigh angle is measured and utilized in this method to construct a phase curve in an activity-specific coordinate frame during a stride. The LA is recognized by matching the curvature of its phase curve to the expected one. The factors affecting the adaptability of the proposed method to gait variations are analyzed and compensated for. The proposed method is evaluated with eight subjects who are asked to perform the three types of activity at two different cadences: 70 steps/min and 110 steps/min. Experimental results show that the proposed classifier outperforms an existing phase variable based classifier in all validation experiments and a ${\boldsymbol{k}}$ -nearest neighbor classifier when using nonsubject-specific training data, indicating that the proposed method has superior adaptability to changes in human and in strides. Moreover, the feature used in the proposed method has demonstrated the potential in quantitatively indicating the extent of neuromotor impairments of patients.
- 13 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 51 (6) , 684-695
Phase Variable Based Recognition of Human Locomotor Activities Across Diverse Gait Patterns
Human locomotor activity (LA) recognition is important in the control of exoskeletons and prostheses and in patient monitoring. This article presents a practical recognition approach that can classify level walking, stair ascent, and stair descent activities across different subjects and diverse gait patterns. The thigh angle is measured and utilized in this method to construct a phase curve in an activity-specific coordinate frame during a stride. The LA is recognized by matching the curvature of its phase curve to the expected one. The factors affecting the adaptability of the proposed method to gait variations are analyzed and compensated for. The proposed method is evaluated with eight subjects who are asked to perform the three types of activity at two different cadences: 70 steps/min and 110 steps/min. Experimental results show that the proposed classifier outperforms an existing phase variable based classifier in all validation experiments and a ${\boldsymbol{k}}$ -nearest neighbor classifier when using nonsubject-specific training data, indicating that the proposed method has superior adaptability to changes in human and in strides. Moreover, the feature used in the proposed method has demonstrated the potential in quantitatively indicating the extent of neuromotor impairments of patients.