Gait generation and transition for a five-link biped robot by Central Pattern Generator

Rashidi, Sahar Farshbaf; Noorani, Mohammad-Reza Sayyed; Shoaran, Maryam; Gholami, Ahmad

doi:10.1109/icrom.2014.6991011

Cited by 3 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NN offers the flexibility of "stacking" several NNs on top of each other, which means, the outputs of a classifier can be connected as inputs to a second NN for control. There are many examples of researchers extracting gaits of bipedal robots [14], [15] or combining them with pattern generation for control by using NNs [16].  Long Short-Term Memory (LSTM) is an addition to NN to provide memory of the previous system states in the NN calculations.…”

Section: B Classifiersmentioning

confidence: 99%

S.A.R.A.H.: The Bipedal Robot with Machine Learning Step Decision Making

Kouppas¹

2018

IJMERR

View full text Add to dashboard Cite

Herein, we describe a custom-made bipedal robot that uses electromagnets for performing movements as opposed to conventional DC motors. The robot uses machine learning to stabilize its self by taking steps. The results of several machine learning techniques for step decision are described. The robot does not use electric motors as actuators. As a result, it makes imprecise movements and is inherently unstable. To maintain stability, it must take steps. Classifiers are required to learn from users about when and which leg to move to maintain stability and locomotion. Classifiers such as Decision tree, Linear/Quadratic Discriminant, Support Vector Machine, K-Nearest Neighbor, and Neural Networks are trained and compared. Their performance/accuracy is noted.

show abstract

Section: B Classifiersmentioning

confidence: 99%

S.A.R.A.H.: The Bipedal Robot with Machine Learning Step Decision Making

Kouppas¹

2018

IJMERR

View full text Add to dashboard Cite

show abstract

“…The NN offers the flexibility of "stacking" several NN on top of each other which means, the outputs of the classifier can connect as inputs to a second NN for controlling. There are a lot of examples of researchers extracting gait for bipedal robots [10], [11] or combining them with pattern generation for control [12]. • Long Short-Term Memory (LSTM) is an addition to NN to provide memory for the previous states of the system in NN's calculation.…”

Section: Introductionmentioning

confidence: 99%

Machine learning comparison for step decision making of a bipedal robot

Kouppas

Meng

King

et al. 2018

2018 3rd International Conference on Control and Robotics Engineering (ICCRE)

View full text Add to dashboard Cite

This paper0 F 1 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.

show abstract