Robotic manipulator motion planning method development using neural network-based intelligent system

The research relevance is determined by the constant development of industry and the use of robotic manipulators in production processes. The study aims to develop an approach to planning the trajectory of a manipulator robot using an intelligent system based on neural networks. An analysis method, as well as special methods such as design, machine learning, integration strategies, and optimisation techniques, were used to achieve this goal. The main results of the study cover a wide range of achievements in the development of methods for planning the motion of robotic manipulators and their integration into real production conditions. The analysis of existing methods for planning the motion of robotic manipulators and a review of intelligent control systems provided a comprehensive picture of the current state of the art. The developed methods of robot manipulator trajectory identified effective control strategies that consider both dynamic and static scenarios. Training a neural network to plan the optimal path of movement made it possible to detect, track and avoid obstacles in real-time. Hierarchical path planning, adaptive neural network control, genetic algorithms for path optimisation, and dynamic prediction for obstacle avoidance were used to integrate the developed methods into a real production environment. The optimisation and improvement of the created approaches have shown positive results in improving the safety and performance of robotic manipulators, reducing the risk of collisions, and avoiding damage to robots. In addition, the implementation of hierarchical trajectory planning and adaptive neural network control contributed to a significant increase in the accuracy and stability of manipulator movements in various production process scenarios. The practical significance of the study is to develop an intelligent control system and methods for planning the movement of robotic manipulators, which contributes to the efficiency and safety of their operation in real production conditions