Estimating Biped Gait Using Spline-Based Probability Distribution Function With Q-Learning

This paper studies the probability distribution functions of the parameters to be learned and optimized in biped gait generation. By formulating the gait pattern generation into a multiobjective optimization problem with consideration of geometric and state constraints, dynamically stable and low en...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial electronics (1982) 2008-03, Vol.55 (3), p.1444-1452
Main Authors: Lingyun Hu, Lingyun Hu, Changjiu Zhou, Changjiu Zhou, Zengqi Sun, Zengqi Sun
Format: Article
Language:English
Subjects:
Biped robot
Constraint optimization
Electronic design automation and methodology
Estimating
Estimation of Distribution Algorithm (EDA)
Gait
gait pattern generation
Humanoid
Humanoid robots
Intelligent control
Intelligent robots
Legged locomotion
Mathematical models
Probability distribution
Probability distribution functions
probability model
Q-learning
Robot control
Robots
Spline
spline function
Spline functions
Stability
Studies
Sun
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper studies the probability distribution functions of the parameters to be learned and optimized in biped gait generation. By formulating the gait pattern generation into a multiobjective optimization problem with consideration of geometric and state constraints, dynamically stable and low energy cost biped gaits are generated and optimized by the proposed method, namely Spline-based Estimation of Distribution Algorithm (EDA) with Q-learning updating rule (EDA_S_Q). Instead of assuming variables as independent ones, the relationship between them is exploited by formulating the corresponding probability models with the Catmull-Rom cubic spline function. Such kind of function is proved to be a suboptimal and adaptive realization of the cubic spline function and is capable of providing high-precision description. Moreover, the probability models are updated autonomously by Q-learning method, which is model-free and adaptive. Thus, EDA_S_Q can deal with complex probability distribution functions without a prior knowledge about the distribution. The biped gait generated by EDA_S_Q has been verified using the simulation model of a humanoid soccer robot Robo-Erectus. It also shows that EDA_S_Q can generate the desired biped gaits autonomously in short learning epochs. An interpretation of the transition probability distribution achieved by EDA_S_Q provides us easy understanding for biped locomotion and better control in humanoid robots.
ISSN:0278-0046
1557-9948
DOI:10.1109/TIE.2007.908526