Rahib H. Abiyev, Nurullah Akkaya, Ersin Aytac, and Dogan Ibrahim


Robot navigation, behaviour-based control, path finding, soccer robot


This paper presents novel behaviour tree (BT) based control and improved path finding algorithm for efficient navigation of holonomic robots used in a soccer team. The hierarchical BT-based control algorithm is proposed for decision making (DM) of robot to reach navigation goals. BT has high- and low-level behaviours and its nodes are operating using certain behaviour rules given in the paper. High-level behaviours are implemented using low-level behaviours. The new behaviours of soccer robots are designed using tree structure. The use of BT approach allows to model complicated situations easily that show advantages of this technique over finite state machines and Petri set widely used in robot control. After DM using BTs, a path finding module is used to determine the path of robot. The next propose of the paper is the design of an improved path finding algorithm. The widely used path finding methods are basically based on artificial potential field method, vector field histogram and A star methods that need certain time for finding feasible path and sometimes do not complete in reasonable short time for real-time operation. Another commonly used algorithm to solve this problem is the rapidly exploring random tree (RRT) algorithm that quickly finds a feasible solution. However, frequently the RRT algorithm alone does not return better results in path length. Here, the integration of RRT with path smoothing techniques is developed. The obtained simulation and experimental results show that the constructed navigation system of soccer robots efficiently finds desirable and feasible solutions in short amount of time.

Important Links:

Go Back