Research on obstacle avoidance path planning of manipulator based on improved RRT-ACO fusion algorithm

To address the challenges faced by traditional Ant Colony Optimization (ACO) in manipulator path planning, such as slow convergence rate, vulnerability to local optima, and excessively lengthy planned paths, this study introduces a novel algorithm for path planning that combines Rapidly-Exploring Random Tree (RRT) with Ant Colony Optimization (ACO). Firstly, the kinematic model of the AUBO-i5 robotic arm is established using the Modified Denavit-Hartenberg (M-DH) method. the application of the Rapidly-exploring Random Tree (RRT) algorithm is employed to conduct a preliminary search for paths. This approach aims to enhance the initial distribution of pheromones in ant colony algorithms and improve heuristic functions. Additionally, an adaptive pheromone volatilization coefficient is introduced to address local optimality issues. Finally, simulation results conducted in MATLAB demonstrate that compared with traditional algorithms, the improved approach exhibits significant enhancements in terms of search time reduction, iteration count decrease, and path length improvement.