Design of effective tour planning for realtime path exploration for controlling autonomous mobile robots

Abstract

There has been progressive development in the field of mobile robots for use in real-time activities due to its diverse application areas. The high-level programming algorithm creates and controls the mobile robots, which are then programmed to adapt to the current environmental circumstances. Consequently, recognising environmental conditions is one of the most difficult challenges in mobile robots, which is important because they are utilised in a variety of real-time applications. In this thesis, an autonomous mobile robot is used to oversee the tour activities. The robot is capable of excellent tour planning and path exploration. The most difficult issues in tour planning are the detection of unknown obstacles and the correct choice of path navigation, both of which make the entire tour process more time-consuming. In order to overcome the aforementioned difficulties, this research proposes an effective potential field integrated prune ART neural network for managing the touring process since it accurately predicts the obstacles in the path and also increases the overall tour navigation by adapting to the surrounding environment. The AlphaBot platform is used to build the efficiency of the system, and the excellence of the system is defined by the accuracy with which obstacles are predicted, the precision with which paths are detected, the time-lapse, the length of the trip, and the overall accuracy of the system. newline