2014
DOI: 10.15625/1813-9663/30/1/3051
|View full text |Cite
|
Sign up to set email alerts
|

Motion control of biped robots in single support phase based on neural network sliding mode approach

Abstract: Tóm tắt. Trong bài báo này trình bày ứng dụng phương pháp điều khiển trượt sử dụng mạng nơron để điều khiển robot hai chân trong pha bước. Bộ điều khiển này tỏ ra hiệu quả và ổn địnhkhi so sánh với bộ điều khiển PD trong trường hợprobot hai chân có độ bất định và có nhiễu tác động lớn.Từ khóa. Robot hai chân, động lực học ngược, điều khiển, mạng nơron.Abstract. In this paper, an application of 5-link biped robotic control model is presented through the neural network sliding mode approach. The proposed control… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2020
2020
2020
2020

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(1 citation statement)
references
References 7 publications
0
1
0
Order By: Relevance
“…Based on the Euler-Lagrange equations, many approaches for deriving the dynamic model of robot manipulators are published [1,6,16,19,20,21]. The important property of dynamic equations, which is often exploited for developing control algorithms (e.g., sliding mode control [8,13], sliding mode control using neural networks [7,13], neural-networkbased control [5,14]), is the skew symmetry that depends on the Coriolis/centrifugal matrix formulation. For satisfying the skew symmetry property, the popular method is to take advantages of Christoffel symbols of the first kind for constructing the Coriolis/centrifugal matrix; but this matrix has to be set up by combining all its elements after calculating every one of them [6,16,19,20,21].…”
Section: Introductionmentioning
confidence: 99%
“…Based on the Euler-Lagrange equations, many approaches for deriving the dynamic model of robot manipulators are published [1,6,16,19,20,21]. The important property of dynamic equations, which is often exploited for developing control algorithms (e.g., sliding mode control [8,13], sliding mode control using neural networks [7,13], neural-networkbased control [5,14]), is the skew symmetry that depends on the Coriolis/centrifugal matrix formulation. For satisfying the skew symmetry property, the popular method is to take advantages of Christoffel symbols of the first kind for constructing the Coriolis/centrifugal matrix; but this matrix has to be set up by combining all its elements after calculating every one of them [6,16,19,20,21].…”
Section: Introductionmentioning
confidence: 99%