Fast-Maneuvering Target Seeking Based on Double-Action Q-Learning
MLDM '07 Proceedings of the 5th international conference on Machine Learning and Data Mining in Pattern Recognition
Tracking under the nonholonomic constraint using cubic navigation laws
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Hi-index | 0.00 |
In this paper, we consider the problem of robot tracking and navigation toward a moving goal. The goal's maneuvers are not a priori known to the robot. Thus, off-line strategies are not effective. To model the robot and the goal, we use geometric rules combined with kinematics equations expressed in a polar representation. The intent of the strategy is to keep the robot between a reference point, called the observer, and the goal. We prove under certain assumptions that the robot navigating using this strategy reaches the moving goal successfully. In the presence of obstacles, the method is combined with an obstacle avoidance algorithm. The robot then moves in two modes, the navigation mode and the obstacle avoidance mode. Simulation of various scenarios highlights the efficiency of the method and provides an instructive comparison between the paths obtained for different reference points.