A HYBRID CBR-NEURAL ADAPTATION ALGORITHM FOR HUMANOID ROBOT CONTROL BASED ON KALMAN BALL TRACKING

Journal Title: ROMANIAN JOURNAL OF TECHNICAL SCIENCES - APPLIED MECHANICS - Year 2012, Vol 57, Issue 2

Abstract

Controlling autonomous, humanoid robots in a dynamic, continuous, and real-time environment is a complex task, especially behavior control and robot ball tracking problems. This paper presents a hybrid Probabilistic CBR-Neural behavior controller for NAO Humanoid soccer. It extends our previously proposed Case-based behavior controller with neural network and Kalman filter (EKF) for ball tracking in the 3D RoboCup soccer simulation scenario [11]. This is to solve the adaptation problem in CBR and to let the robot learn the Goal-scoring behavior cases that should be executed in real-time. The learned behavior depends highly on the ball tracking results, which is shown using different experiments presented. Our experiments are conducted on the Goal-Score behavior for adapting actions of an attacker humanoid robot. The integration of neural network module for case adaptation shows a very high performance accuracy that reaches average 92.3% by integrating the ball tracking module with Kalman filter. The algorithm modules, results and future research direction are discussed in this paper.

Authors and Affiliations

Bassant Mohamed ELBAGOURY, Abdel-Badeeh M. SALEM

Keywords

Related Articles

INVERSE DYNAMICS OF THE CINCINNATI-MILACRON WRIST ROBOT

Recursive matrix relations in dynamics of the Cincinnati-Milacron wrist robot are established in this paper. The prototype of this mechanism is a three-degrees-of freedom spherical system with six moving links and three...

INTERNAL REACTION FORCES IN DYNAMICS OF A PLANAR PARALLEL MANIPULATOR

Three identical legs connecting to the moving platform of a planar parallel manipulator are located in the same vertical plane. Knowing the motion of the platform, we determine the positions, velocities and accelerations...

NUMERICAL SIMULATIONS OF NAKAZIMA FORMABILITY TESTS WITH PREDICTION OF FAILURE

This paper presents results of numerical simulations of the Nakazima test with determination of formability without using the forming limit curve. The onset of localized necking has been determined using the criterion ba...

THE POTENTIAL OF THE 3-UPU TOPOLOGY FOR TRANSLATIONAL PARALLEL MANIPULATORS AND A PROCEDURE TO SELECT THE BEST ARCHITECTURE FOR A GIVEN TASK

The 3-UPU three degrees of freedom fully parallel manipulator, where U and P are for universal and prismatic pair respectively, is a very well known manipulator that can provide the platform with three degrees of freedom...

A GENERALIZATION OF THE GIRSANOV THEOREMS ON THE HILBERT SPACE

This paper gives a generalization of the Girsanov theorems on the separable Hilbert space. And we also give a characterization on the Hilbert space of the Wiener processes, using the quadratic variance process.

Download PDF file
  • EP ID EP178874
  • DOI -
  • Views 138
  • Downloads 0

How To Cite

Bassant Mohamed ELBAGOURY, Abdel-Badeeh M. SALEM (2012). A HYBRID CBR-NEURAL ADAPTATION ALGORITHM FOR HUMANOID ROBOT CONTROL BASED ON KALMAN BALL TRACKING. ROMANIAN JOURNAL OF TECHNICAL SCIENCES - APPLIED MECHANICS, 57(2), 206-216. https://europub.co.uk/articles/-A-178874