Machine learning comparison for step decision making of a bipedal robot

This paper1 presents the results of several machine learning techniques for step decision in a bipedal robot. The custom developed bipedal robot does not utilize electric motors as actuators and as a result has the disadvantage of imprecise movements. The robot is inherently unstable and maintain its stability by making steps. The classifiers had to learn when and which leg must be moved in order to maintain stability and locomotion. Methods like: Decision tree, Linear/Quadratic Discriminant, SVM, KNN and Neural Networks were trained. The results of their performance/accuracy are noted.

[1]  Hamidreza Memarzadeh-Tehran,et al.  Technique to estimate human reaction time based on visual perception , 2017, Healthcare technology letters.

[2]  Toru Yamaguchi,et al.  Realization of a high speed biped using modern control theory , 1984 .

[3]  W. H. ElMaraghy,et al.  A neural network solution for bipedal gait synthesis , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[4]  Ahmad Ghanbari,et al.  Gait generation and transition for a five-link biped robot by Central Pattern Generator , 2014, 2014 Second RSI/ISM International Conference on Robotics and Mechatronics (ICRoM).

[5]  J. Nielsen.  How we Walk: Central Control of Muscle Activity during Human Walking , 2003, The Neuroscientist : a review journal bringing neurobiology, neurology and psychiatry.

[6]  Yasuo Kuniyoshi,et al.  Falling motion control for humanoid robots while walking , 2007, 2007 7th IEEE-RAS International Conference on Humanoid Robots.

[7]  Yuzhong Zhang,et al.  An on-line gait generator for bipedal walking robot based on neural networks , 2011, 2011 6th IEEE Conference on Industrial Electronics and Applications.

[8]  J. Botwinick,et al.  Age differences in finger, jaw, and foot reaction time to auditory stimuli. , 1955, Journal of gerontology.

[9]  Julia T. Choi,et al.  Adaptation reveals independent control networks for human walking , 2007, Nature Neuroscience.

[10]  Yang Feng,et al.  Learning effective Gait features using LSTM , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[11]  Tae-Yong Choi,et al.  Falling avoidance of biped robot using state classification , 2008, 2008 IEEE International Conference on Mechatronics and Automation.

[12]  Chen-Yuan Chen,et al.  The development on obstacle avoidance design for a humanoid robot based on four ultrasonic sensors for the learning behavior and performance , 2010, 2010 IEEE International Conference on Industrial Engineering and Engineering Management.

[13]  Jessy W. Grizzle,et al.  Reduced-order framework for exponential stabilization of periodic orbits on parameterized hybrid zero dynamics manifolds: Application to bipedal locomotion , 2017 .

[14]  Khairul Salleh Mohamed Sahari,et al.  Multiple sequence behavior recognition on humanoid robot using long short-term memory (LSTM) , 2014, 2014 IEEE International Symposium on Robotics and Manufacturing Automation (ROMA).

[15]  Takao Sato,et al.  Slope-Walking of a Biped Robot with K Nearest Neighbor method , 2009, 2009 Fourth International Conference on Innovative Computing, Information and Control (ICICIC).