Reconstruction of Human Skills by Using PCA and Transferring them to a Robot

2014 ◽  
Vol 26 (1) ◽  
pp. 51-58 ◽  
Author(s):  
Masahiro Takeuchi ◽  
◽  
Jun Shimodaira ◽  
Yuki Amaoka ◽  
Shinsuke Hamatani ◽  
...  
Keyword(s):  
Cognitive Skills ◽  
Principal Component ◽  
Human Movement ◽  
Motor Program ◽  
Table Tennis ◽  
Human Opponent ◽  
Human Skills ◽  
External Stimuli ◽  
Generalized Motor Program ◽  
Table Tennis Player

This paper discusses human skills enabling rapid adaptation to a changing environment, e.g., when a human table tennis player hits an incoming ball, and describes how to transfer these skills to a robot. Human skills are classified into motor and cognitive. Motor skills are functions involving precise limb movement with the intent to perform a specific act, i.e., hitting a ball. Cognitive skills are functions involving meaningful responses to external stimuli. We extract these skills from observing human movement using principal component analysis and generalize these skills as a schema for a generalized motor program. We also describe table tennis matches between a human opponent and a robot to which these skills have been transferred.

scholarly journals A Deep Learning Approach for Table Tennis Forehand Stroke Evaluation System Using an IMU Sensor

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Sahar S. Tabrizi ◽  
Saeid Pashazadeh ◽  
Vajiheh Javani
Keyword(s):  
Evaluation System ◽  
Low Cost ◽  
Estimation Error ◽  
Weighted Average ◽  
Principal Component ◽  
Training System ◽  
Table Tennis ◽  
Sports Activity ◽  
Nonlinear Regression Models ◽  
Shadow Play

Psychological and behavioral evidence suggests that home sports activity reduces negative moods and anxiety during lockdown days of COVID-19. Low-cost, nonintrusive, and privacy-preserving smart virtual-coach Table Tennis training assistance could help to stay active and healthy at home. In this paper, a study was performed to develop a Forehand stroke’ performance evaluation system as the second principal component of the virtual-coach Table Tennis shadow-play training system. This study was conducted to show the effectiveness of the proposed LSTM model, compared with 2DCNN and RBF-SVR time-series analysis and machine learning methods, in evaluating the Table Tennis Forehand shadow-play sensory data provided by the authors. The data was generated, comprising 16 players’ Forehand strokes racket’s movement and orientation measurements; besides, the strokes’ evaluation scores were assigned by the three coaches. The authors investigated the ML models’ behaviors changed by the hyperparameters values. The experimental results of the weighted average of RMSE revealed that the modified LSTM models achieved 33.79% and 4.24% estimation error lower than 2DCNN and RBF-SVR, respectively. However, the R ¯ 2 results show that all nonlinear regression models are fit enough on the observed data. The modified LSTM is the most powerful regression method among all the three Forehand types in the current study.

Optimizing Generalized Motor Program and Parameter Learning

2000 ◽  
Vol 71 (1) ◽  
pp. 10-24 ◽  
Author(s):  
Qin Lai ◽  
Charles H. Shea ◽  
Gabriele Wulf ◽  
David L. Wright
Keyword(s):  
Motor Program ◽  
Parameter Learning ◽  
Generalized Motor Program

Continuous Concurrent Feedback Degrades Skill Learning: Implications for Training and Simulation

1997 ◽  
Vol 39 (4) ◽  
pp. 509-525 ◽  
Author(s):  
Richard A. Schmidt ◽  
Gabriele Wulf
Keyword(s):  
Temporal Pattern ◽  
Closed Loop ◽  
Motor Program ◽  
Skill Learning ◽  
Discrete Movement ◽  
On Line ◽  
Continuous Feedback ◽  
The Stability ◽  
Generalized Motor Program

In two experiments we investigated the role of continuous concurrent visual feedback in the learning of discrete movement tasks. During practice the learner's actions either were or were not displayed on-line during the action; in both conditions the participant received kinematic feedback about errors afterward. Learning was evaluated in retention tests on the following day. We separated (a) errors in the fundamental spatial-temporal pattern controlled by the generalized motor program from (b) errors in scaling controlled by parameterization processes. During practice concurrent feedback improved parameterization but tended to decrease program stability. Based on retention tests, earlier practice with continuous feedback generally interfered with the learning of an accurate motor program and reduced the stability of time parameterization. Continuous feedback during acquisition degrades the learning of not only closed-loop processes in slower movements (as has been found in earlier studies) but also motor programs and their parameterization in more rapid tasks. Implications for feedback in training and simulation are discussed.

Activity of spindle afferents from cat anterior thigh muscles. III. Effects of external stimuli

1985 ◽  
Vol 54 (3) ◽  
pp. 578-591 ◽  
Author(s):  
G. E. Loeb ◽  
J. A. Hoffer ◽  
W. B. Marks
Keyword(s):  
Motor Program ◽  
Sartorius Muscle ◽  
Muscle Spindle Afferents ◽  
Implanted Electrodes ◽  
Hamstring Muscles ◽  
Highly Sensitive ◽  
Motoneuron Activity ◽  
Fusimotor System ◽  
External Stimuli ◽  
Awake Cats

Chronically implanted electrodes were used to record the activity of identified single muscle spindle afferents in awake cats during responses to various types of manual and electrical stimulation. During vigorous cyclical responses such as shaking and scratching, spindle afferents generally maintained at least some activity during both lengthening and shortening of the parent muscle, indicating that the programs for these movements include both extra- and intrafusal recruitment. During noncyclical responses such as ipsilateral limb withdrawal and crossed-extension, spindle activity was modest and poorly correlated with extrafusal activity. Weak cutaneous nerve shocks during walking elicited complex excitatory and inhibitory phase-dependent reflexes in the various muscles studied but caused relatively little change in spindle afferent activity, indicating a lack of correlation between alpha and gamma motoneuron activity. A primary and a secondary afferent from sartorius muscle were recorded simultaneously during walking cycles that were perturbed by electrically induced twitches of the antagonist hamstring muscles; both demonstrated highly sensitive, short latency responses to the resulting skeletal motion, consistent with their previously suggested roles in detecting small brief mechanical perturbations. The degree to which fusimotor responses were correlated with extrafusal responses to somatosensory perturbations was highly dependent on the specific nature of the stimulus and the response. Fusimotor reprogramming of the spindle sensitivity appears to be a feature of cyclical movements that are presumably under proprioceptive control, whereas brief perturbations within the context of a particular motor program may be ignored by the fusimotor system.

Sign in / Sign up

Export Citation Format

Share Document