Innovative Path Planning Algorithm for an Autonomous Robot with Low Computational Cost

The processing of data maps in order to find the best solution to transverse between two points is a key task of an autonomous robot. The algorithm often used for this task must also define the computational power requirements of the embedded processor in the system to optimise the solution with the least number of steps. Low end processors can be used contrary to traditional computers. This paper presents a simplified path solving algorithm for known and unknown environments where the robot range is limited to the size of the map created within the computer internal memory. The map can be preloaded with obstacles expected to be encountered. Alternatively, the robot can be switched to discover mode, where information about its environment is gathered on-the-fly using a range sensor. Two path planning algorithms have been simulated in this study to analyse the most efficient execution to be implemented on the platform with a micro-controller with the A∗ algorithm showing the superior performance and lower computational cost in comparison with Djickstra.