Xupeng Ai

Xupeng Ai

Auto-generated profile, based on publicly available information

Xupeng Ai

Department of Mechanical Engineering, Columbia University, New York, NY, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 June 2020 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Closed access
YSYogesh Singh
Yogesh Singh
APAntonio Prado
Antonio Prado
DMDario Martelli
Dario Martelli
FPFitsum E. Petros
Fitsum E. Petros
XAXupeng Ai
Xupeng Ai
SASunil K. Agrawal
Sunil K. Agrawal
Virtual Reality is a versatile platform to study human behavior in simulated environments and to develop interventions for functional rehabilitation. In this work, we designed a dual-task paradigm in a virtual environment where both tasks demand motor skills. Twenty-one healthy adults (mean age: 24.1 years) participated in this study. The experiment involved three conditions - normal overground walking, catch and throw a ball while standing, and catch and throw a ball while walking overground -all in the virtual environment. We investigated the dual-task gait characteristics and their correlations with outcomes from cognitive assessments. Results show that subjects walk conservatively with smaller stride lengths, larger stride widths and stride time while catching and throwing. However, they are able to throw the balls more accurately at the target and achieve higher scores. During the dual-task throw, we observed that the participants threw more balls during the stance phase of the gait when the foot was in the terminal stance and pre-swing region. During this region, the body has forward momentum. In addition, the changes in gait characteristics during dual-task throw correlate well with outcome measures in standardized cognitive tests. This study provides a new and engaging paradigm to analyze dual-motor-task cost in a virtual reality environment and it can be used as a basis to compare strategies adopted by different population groups with healthy young adults to execute coordinated motor tasks.

9 November 2022 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
XAXupeng Ai
Xupeng Ai
VSVictor Santamaria
Victor Santamaria
JCJiawei Chen
Jiawei Chen
BHBoce Hu
Boce Hu
CZChenfei Zhu
Chenfei Zhu
SASunil K. Agrawal
Sunil K. Agrawal
Seated postural limit defines the boundary of a region such that for any excursions made outside this boundary a subject cannot return the trunk to the neutral position without additional external support. The seated postural limits can be used as a reference to provide assistive support to the torso by the Trunk Support Trainer (TruST). However, fixed boundary representations of seated postural limits are inadequate to capture dynamically changing seated postural limits during training. In this study, we propose a conceptual model of dynamic boundary of the trunk center by assigning a vector that tracks the postural-goal direction and trunk movement amplitude during a sitting task. We experimented with 20 healthy subjects. The results support our hypothesis that TruST intervention with an assist-as-needed force controller based on dynamic boundary representation could achieve more significant sitting postural control improvements than a fixed boundary representation. The second contribution of this paper is that we provide an effective approach to embed deep learning into TruST’s real-time controller design. We have compiled a 3D trunk movement dataset which is currently the largest in the literature. We designed a loss function capable of solving the gate-controlled regression problem. We have proposed a novel deep-learning roadmap for the exploration study. Following the roadmap, we developed a deep learning architecture, modified the widely used Inception module, and then obtained a deep learning model capable of accurately predicting the dynamic boundary in real-time. We believe that this approach can be extended to other rehabilitation robots towards designing intelligent dynamic boundary-based assist-as-needed controllers.

23 July 2024 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
XAXupeng Ai
Xupeng Ai
VSVictor Santamaria
Victor Santamaria
SASunil K. Agrawal
Sunil K. Agrawal
Extended reality (XR) technology combines physical reality with computer synthetic virtuality to deliver immersive experience to users. Virtual reality (VR) and augmented reality (AR) are two subdomains within XR with different immersion levels. Both of these have the potential to be combined with robot-assisted training protocols to maximize postural control improvement. In this study, we conducted a randomized control experiment with sixty-three healthy subjects to compare the effectiveness of robot-assisted posture training combined with VR or AR against robotic training alone. A robotic Trunk Support Trainer (TruST) was employed to deliver assistive force at the trunk as subjects moved beyond the stability limits during training. Our results showed that both VR and AR significantly enhanced the training outcomes of the TruST intervention. However, the VR group experienced higher simulator sickness compared to the AR group, suggesting that AR is better suited for sitting posture training in conjunction with TruST intervention. Our findings highlight the added value of XR to robot-assisted training and provide novel insights into the differences between AR and VR when integrated into a robotic training protocol. In addition, we developed a custom XR application that suited well for TruST intervention requirements. Our approach can be extended to other studies to develop novel XR-enhanced robotic training platforms.

8 May 2023 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
XAXupeng Ai
Xupeng Ai
VSVictor Santamaria
Victor Santamaria
IOIsirame Omofuma
Isirame Omofuma
SASunil K. Agrawal
Sunil K. Agrawal
The boundary-based assist-as-needed (BAAN) force field is widely used in robotic rehabilitation and has shown promising results in improving trunk control and postural stability. However, the fundamental understanding of how the BAAN force field affects the neuromuscular control remains unclear. In this study, we investigate how the BAAN force field impacts muscle synergy in the lower limbs during standing posture training. We integrated virtual reality (VR) into a cable-driven Robotic Upright Stand Trainer (RobUST) to define a complex standing task that requires both reactive and voluntary dynamic postural control. Ten healthy subjects were randomly assigned to two groups. Each subject performed 100 trials of the standing task with or without assistance from the BAAN force field provided by RobUST. The BAAN force field significantly improved balance control and motor task performance. Our results also indicate that the BAAN force field reduced the total number of lower limb muscle synergies while concurrently increasing the synergy density (i.e., number of muscles recruited in each synergy) during both reactive and voluntary dynamic posture training. This pilot study provides fundamental insights into understanding the neuromuscular basis of the BAAN robotic rehabilitation strategy and its potential for clinical applications. In addition, we expanded the repertoire of training with RobUST that integrates both perturbation training and goal-oriented functional motor training within a single task. This approach can be extended to other rehabilitation robots and training approaches with them.

13 September 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
XAXupeng Ai
Xupeng Ai
SASunil K. Agrawal
Sunil K. Agrawal
Dynamic postural control during sitting is essential for functional mobility and daily activities. Extended reality (XR) presents a promising solution for posture training in addressing conventional training limitations related to patient accessibility and ecological validity. We developed a remote XR rehabilitation system with markerless motion tracking for sitting posture training. Forty-two healthy subjects participated in this proof-of-concept pilot study. Each subject completed 24 rounds of multi-directional reach tasks using the system and 24 rounds without it. Motion data were collected via online meetings using built-in camera in the user's laptop. Functional reach test scores were analyzed to assess the impact of the system on motor performance. Four standard questionnaires were used to assess the effects of this system on presence, simulator sickness, engagement, and enjoyment. Our results indicate that the remote XR training system significantly improved functional reach performance and proved highly effective for telerehabilitation. XR interaction also enhanced training engagement and enjoyment. By bridging the spatial gap between patients and therapists, this system enables personalized and engaging home-based intervention. Additionally, it facilitates more natural movements by eliminating body marker constraints and laboratory limitations. This study should serve as a stepping stone to advancing novel remote XR rehabilitation systems.

6 December 2023 in Bioengineering
Verified
Journal Article
Open access
PDF file
IOIsirame Omofuma
Isirame Omofuma
VSVictor Santamaria
Victor Santamaria
XAXupeng Ai
Xupeng Ai
SASunil K. Agrawal
Sunil K. Agrawal
This study characterizes the effects of a postural training program on balance and muscle control strategies in a virtual reality (VR) environment. The Robotic Upright Stand Trainer (RobUST), which applies perturbative forces on the trunk and assistive forces on the pelvis, was used to deliver perturbation-based balance training (PBT) in a sample of 10 healthy participants. The VR task consisted of catching, aiming, and throwing a ball at a target. All participants received trunk perturbations during the VR task with forces tailored to the participant’s maximum tolerance. A subgroup of these participants additionally received assistive forces at the pelvis during training. Postural kinematics were calculated before and after RobUST training, including (i) maximum perturbation force tolerated, (ii) center of pressure (COP) and pelvic excursions, (iii) postural muscle activations (EMG), and (iv) postural control strategies (the ankle and hip strategies). We observed an improvement in the maximum perturbation force and postural stability area in both groups and decreases in muscle activity. The behavior of the two groups differed for perturbations in the posterior direction where the unassisted group moved towards greater use of the hip strategy. In addition, the assisted group changed towards a lower margin of stability and higher pelvic excursion. We show that training with force assistance leads to a reactive balance strategy that permits pelvic excursion but that is efficient at restoring balance from displaced positions while training without assistance leads to reactive balance strategies that restrain pelvic excursion. Patient populations can benefit from a platform that encourages greater use of their range of motion.