Backward walking simulation of humans using optimization

Kwon, Hyun-Jung; Xiang, Yujiang; Bhatt, Ramesh S.; Rahmatalla, Salam; Arora, Jasbir S.; Abdel‐Malek, Karim

doi:10.1007/s00158-013-1039-x

Cited by 12 publications

(13 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Walker et al also observed that normoglycemic women failed to lose body fat after 12 weeks of exercise in a walking program 23 ) . It has also been demonstrated that the joint torque profiles of the hip and knee in BW are quite similar to those of FW with a reverse sequence, but with different time durations of flexion and extension 24 ) . These findings are also supportive of the lack of impact on body composition observed in the FWG and the BWG in the present study.…”

Section: Discussionmentioning

confidence: 90%

Effect of Forward and Backward Locomotion Training on Anaerobic Performance and Anthropometrical Composition

et al. 2014

View full text Add to dashboard Cite

[Purpose] Forward walking (FW) and backward walking (BW) on a treadmill is a common tool for lower extremity rehabilitation in the clinical setting. The purpose of this study was to evaluate the effects on anaerobic performance and anthropometrical adaptations during FW and BW on a treadmill. [Subjects and Methods] A convenience sample of thirty healthy male subjects with a mean age of 20.93 ± 2.54 years participated in this study. Subjects were divided into 2 groups, a Forward Walking Group (FWG) (n=15) and a Backward Walking Group (BWG) (n=15), which performed FW and BW on a treadmill at 10° inclination, respectively. The training consisted of three sessions per week for 6 weeks. Study outcomes such as anaerobic performance and anthropometrical body composition were measured at pre- and post-intervention. [Results] Both FW and BW improved anaerobic performance significantly, and the BW group showed better performance than FW. However, changes in anthropometrical body composition were found to be not significant after six weeks of intervention in both the FW and BW groups. [Conclusions] BW training in rehabilitation can be considered more effective than FW at improving anaerobic performance. We also conclude that six weeks of FW and BW training is insufficient for eliciting changes in the body composition.

show abstract

Section: Discussionmentioning

confidence: 90%

Effect of Forward and Backward Locomotion Training on Anaerobic Performance and Anthropometrical Composition

et al. 2014

View full text Add to dashboard Cite

show abstract

“…Since its development, PD has been used to simulate different motion tasks and scenarios (J. H. Kim, et al, 2008; J. H. Kwon, et al, 2014;, 2012. The inputs for each simulation take two forms: avatar-based and task-based.…”

Section: Digital Human Model and Physics-based Motion Predictionmentioning

confidence: 99%

Neural network for dynamic human motion prediction

Bataineh

Marler

Abdel‐Malek

et al. 2016

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

Digital human models (DHMs) are critical for improved designs, injury prevention, and a better understanding of human behavior. Although many capabilities in the field are maturing, there are still opportunities for improvement, especially in motion prediction. Thus, this work investigates the use of an artificial neural network (ANN), specifically a general regression neural network (GRNN), to provide real-time computation of DHM motion prediction, where the underlying optimization problems are large and computationally complex. In initial experimentation, a GRNN is used successfully to simulate walking and jumping on a box while using physics-based human simulations as training data. Compared to direct computational simulations of dynamic motion, use of GRNN reduces the calculation time for each predicted motion from 1-40 minutes to a fraction of a second with no noticeable reduction in accuracy. This work lays the foundation for studying the effects of changes to training regiments on human performance.

show abstract

“…Nevertheless, an outstanding walking planning result with machine learning may need a great amount of online training under various scenes, which will be a huge cost on time and energy. Approaches with interpolation also are a popular method in walking planning, and there are many different interpolation functions are used, such as the high-order polynomial method [18], cubic spline interpolation [19], B-spline interpolation [20], and so on. The parameters of interpolation are calculated by key frame data and the continuous pose data are calculated by the interpolation.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Omni-directional Walking Method with Fuzzy Interpolation for Biped Robots

Shi¹,

Li²,

Chen³

et al. 2016

IJNDC

View full text Add to dashboard Cite

Omni-directional walking is an important part for biped robots. Whereas, the problems of complex model, low stability, low flexibility, etc., existing in walking planning of biped robots, attract interests of many researchers. This paper proposes an adaptive omni-directional walking method with fuzzy interpolation (OW-FI) applied to a fast-stable omni-directional walking. A new separated omni-directional walking method consisting of straight walking, based on the improve Hermite interpolation, and rotation is designed to simplify the walking model and achieve a good key frame data selection. The mapping relationship between poses and actuators' angular speeds is then constructed by walking transforming model based on kinematics. In order to implement a stable and adaptive walking, a fuzzy approach to walking parameters adjustment is presented, where the step length and rotational speed of omni-directional walking are controlled fuzzily. The results of simulations and experiments demonstrate that the proposed method has better properties in adaptability and stability than the competing methods.

show abstract

Backward walking simulation of humans using optimization

Cited by 12 publications

References 32 publications

Effect of Forward and Backward Locomotion Training on Anaerobic Performance and Anthropometrical Composition

Effect of Forward and Backward Locomotion Training on Anaerobic Performance and Anthropometrical Composition

Neural network for dynamic human motion prediction

Adaptive Omni-directional Walking Method with Fuzzy Interpolation for Biped Robots

Contact Info

Product

Resources

About