A method for increasing the teamwork collaboration based on the online detection of robot sustainability status and falling direction

Nowadays, robot stability is one of the most important challenges of 3D Soccer Simulation League in the science of robotics. Loss of balance and falling on the ground by colliding two robot players, is one of the most important topics in the team-collaboration-bots, and this can beneficial for the opposing team. we present a new approach for detecting robot stability, based on information derived from the 3D soccer simulation server (rcssserver3D). In this article, two data sets using the positions of the joints of the robot legs are generated. One of the dataset is based on the sustainability of the robot and the other is based on the falling direction (left and right). A model based on Support Vector Machines )SVM( learning algorithms, Artificial Neural Networks (ANN) and Logistic Regression, are employed. we add this model to a 3D soccer simulation platform, in order to recognize the stability and falling or not falling situation (direction) online. By this model stability of each robot is notified to his teammate and consequently adequate information is provided for best performance. Our results show that using this method in the 3D soccer simulation, increases the number of goals and the team performance. We also show that SVM classifier with the RBF kernel and optimized parameters increases our model’s performance, because the SVM classifier performs better than the other two models on the small-sizedata sets.

کلیدواژه ها:

3D soccer simulation league ، SVM method ، logistic regression ، neural networks ، humanoid robots and stability