Recent Advances in Robotic Systems 2016
DOI: 10.5772/63746
|View full text |Cite
|
Sign up to set email alerts
|

Muscle‐Like Compliance in Knee Articulations Improves Biped Robot Walkings

Abstract: This chapter focuses on the compliance effect of dynamic humanoid robot walking. This compliance is generated with an articular muscle emulator system, which is designed using two neural networks (NNs). One NN models a muscle and a second learns to tune the proportional integral derivative (PID) of the articulation DC motor, allowing it to behave analogously to the muscle model. Muscle emulators are implemented in the knees of a three-dimensional (3D) simulated biped robot. The simulation results show that the… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

1
1
0

Year Published

2017
2017
2024
2024

Publication Types

Select...
3
1

Relationship

2
2

Authors

Journals

citations
Cited by 4 publications
(2 citation statements)
references
References 43 publications
1
1
0
Order By: Relevance
“…Resulting joint angles are qualitatively similar to human walking cycle [17,18], especially hip and knee joints that are similar to those in [19], where articular angles of the human hip, knee, and ankle are compared to those with a rigid and non rigid human foot soles. Walking simulation starts from double support phase.…”
Section: A Walking With Constant Speedsupporting
confidence: 53%
“…Resulting joint angles are qualitatively similar to human walking cycle [17,18], especially hip and knee joints that are similar to those in [19], where articular angles of the human hip, knee, and ankle are compared to those with a rigid and non rigid human foot soles. Walking simulation starts from double support phase.…”
Section: A Walking With Constant Speedsupporting
confidence: 53%
“…Difference between human ankle behavior and simulated one may come from the difficulty to produce a realistic model of the foot (number of muscles, sole flexibility) and thus to simulate correctly the foot/ground contact. In the OpenSim model, the foot's sole is almost rigid and creates some changes in the joint angle behavior compared to the human [29].…”
Section: A Normal Gaitmentioning
confidence: 99%