Path planning of the autonomous mobile robot by using real-time rolling risk estimation with fuzzy inference

Along with the advancement of research on intelligent robotics, the situation where the robot moves independently and performs work in real environment is expanding. In such situation, it is one of the highest priority for the autonomous mobile robot to reach the destination point without failure. Therefore, we consider the transfer of the mobile robot on pre-planned paths to a partially observed environment. When the mobile robot encounters danger in the observing environment and determines to take a detour, it is necessary to re-plan safe routes in a short time. In this study, we focused on the rollover risk of mobile robot. And we simulate the autonomous rerouting of the mobile robot for finding a more secure route such that it can safely arrive at the destination point, whenever it senses high possibility of rollover. By using fuzzy inference to judge rollover risk, the mobile robot judges the necessity of route change according to the magnitude of risk. We also aimed to quickly perform rerouting by using the D∗ Lite algorithm in real-time for robot movement. We propose a method to realize route planning modification based on evaluation and judgment of rollover risk by combining fuzzy inference and D∗ Lite algorithm. As a result, we confirm that the autonomous mobile robot can reach the destination point by real-time evaluation of the risk and taking detour action as necessary. Experiments are conducted through computer simulation using a virtual mobile robot and a 3D path based on graph theory. Finally, we discuss about the result of the simulation.