Gaussian Process Trajectory Learning and Synthesis of Individualized Gait Motions

Hong, Jisoo; Chun, Changmook; Kim, Seung-Jong; Park, Frank C.

doi:10.1109/tnsre.2019.2914095

Cited by 23 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This reduction in forces can even be larger than the reduction in the moment contribution from an impedance controller. It is important to mention here that our approach does not require the use of biosensors, which increases complexity in terms of data acquisition and subsequent signal processing [32][33][34][35]. However, there is one shortcoming of path modification that was determined from experimentation using this control module.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Musculoskeletal Model for Path Generation and Modification of an Ankle Rehabilitation Robot

Jamwal

Hussain

Tsoi³

et al. 2020

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

While newer designs and control approaches are being proposed for rehabilitation robots, vital information from the human musculoskeletal system should also be considered. Incorporating knowledge about joint biomechanics during the development of robot controllers can enhance the safety and performance of robot-aided treatments. In the present work, the optimal path or trajectories of a parallel ankle rehabilitation robot were generated by minimizing joint reaction moments and the tension along ligaments and muscle-tendon units. The simulations showed that using optimized robot paths, user efforts could be reduced to 80%, thereby ensuring less strain on weaker or stiffer ligaments, etc. Additionally, to limit the moments applied by the robot in stiff or constrained directions, the intended robot path was modified to move the commanded position in the direction opposite to that of the position error. Such online modification of the robot path can lead to a reduction in forces applied by a robot to the subject. Simulation results and experimental findings with healthy subjects using an ankle rehabilitation robot prototype and subsequent statistical analysis further validated that path modification based on ankle joint biomechanics results in a reduction in undesired forces experienced by human users during treatment. Index Terms-ankle joint musculoskeletal modeling, optimization of muscle forces, parallel ankle rehabilitation robot, robot path generation and modification I.

show abstract

Section: Discussionmentioning

confidence: 99%

“…still remain to be addressed. Hong et al proposed Gaussian process-based trajectory learning to identify individual musculoskeletal parameters from gait motions at different speeds in healthy subjects [32]. This model considers individual subjects' physiological characteristics, such as height, weight, and age.…”

Section: Takedownmentioning

confidence: 99%

Musculoskeletal Model for Path Generation and Modification of an Ankle Rehabilitation Robot

Jamwal

Hussain

Tsoi³

et al. 2020

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

show abstract

“…Yun et al [18], Wu et al [20], and Hong et al [21] utilized Gaussian Process Regression (GPR) to create a mapping from body parameters to gait patterns. Since their data sets contain only gait patterns at discrete fixed values of walking speeds, their performance is bound to be unsatisfactory when self-paced walking is needed.…”

Section: Lim Et Al Used a Multi-layer Perceptron Neural Network (Mlpmentioning

confidence: 99%

“…Since their data sets contain only gait patterns at discrete fixed values of walking speeds, their performance is bound to be unsatisfactory when self-paced walking is needed. In addition, Hong et al [21] utilized the Gaussian Process Dynamic Model (GPDM) as a nonlinear dimensionality reduction technique to represent gait patterns. Nevertheless, modeling gait patterns with GPDM causes an error up to 20%.…”

Section: Lim Et Al Used a Multi-layer Perceptron Neural Network (Mlpmentioning

confidence: 99%

“…Recently, with the rapid development of machine learning techniques, researchers have turned to learning-based methods, considering gait generation as a regression problem [17]- [21]. Typically, these works collect a database of healthy people, which contains the gait patterns of many subjects walking in various states and their body parameters.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Individualized Gait Generation for Rehabilitation Robots Based on Recurrent Neural Networks

Zhou

Liang

Huang

et al. 2021

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Individualized reference gait patterns for lower limb rehabilitation robots can greatly improve the effectiveness of rehabilitation. However, previous methods can only generate customized gait patterns at several fixed discrete walking speeds and generating gaits at continuously varying speeds and stride lengths remains unsolved. This work proposes an individualized gait pattern generation method based on a recurrent neural network (RNN), which is proficient in series modeling. We collected the largest gait data set of this kind, which consists of 4,425 gait patterns from 137 subjects. Using this data set, we trained an RNN to create a function mapping from body parameters and gait parameters to a gait pattern. The experimental results indicate that our model is able to generate gait patterns at continuously varying walking speeds and stride lengths while also reducing the errors in the ankle, knee, and hip measurements by 12.83%, 20.95%, and 28.25%, respectively, compared to previous state-of-the-art method.

show abstract

Application of motion trajectory recognition based on remote sensing image optical processing in optimizing swimming training schemes

Jiang

2023

Opt Quant Electron

View full text Add to dashboard Cite

Gaussian Process Trajectory Learning and Synthesis of Individualized Gait Motions

Cited by 23 publications

References 27 publications

Musculoskeletal Model for Path Generation and Modification of an Ankle Rehabilitation Robot

Musculoskeletal Model for Path Generation and Modification of an Ankle Rehabilitation Robot

Individualized Gait Generation for Rehabilitation Robots Based on Recurrent Neural Networks

Application of motion trajectory recognition based on remote sensing image optical processing in optimizing swimming training schemes

Contact Info

Product

Resources

About