DocumentCode :
992850
Title :
Estimating Biped Gait Using Spline-Based Probability Distribution Function With Q-Learning
Author :
Hu, Lingyun ; Zhou, Changjiu ; Sun, Zengqi
Author_Institution :
Singapore Polytech., Singapore
Volume :
55
Issue :
3
fYear :
2008
fDate :
3/1/2008 12:00:00 AM
Firstpage :
1444
Lastpage :
1452
Abstract :
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.
Keywords :
learning (artificial intelligence); legged locomotion; optimisation; probability; splines (mathematics); Q-learning updating rule; Robo-Erectus; biped gait estimation; biped gait generation; biped locomotion; cubic spline function; distribution algorithm; gait pattern generation; geometric constraint; humanoid robots; humanoid soccer robot; multiobjective optimization problem; spline-based estimation; spline-based probability distribution function; state constraint; Biped robot; Estimation of Distribution Algorithm (EDA); Q-learning; biped robot; estimation of distribution algorithm; gait pattern generation; probability model; spline function;
fLanguage :
English
Journal_Title :
Industrial Electronics, IEEE Transactions on
Publisher :
ieee
ISSN :
0278-0046
Type :
jour
DOI :
10.1109/TIE.2007.908526
Filename :
4391037
Link To Document :
بازگشت