Hongyue Liu
Adaptive, ant colony optimisation, mobile robot, path planning, pheromones
The path planning of mobile robot involves many interdisciplinary technologies, such as environment perception and data processing, which is an important link in the research of mobile robot navigation technology. The traditional ant colony algorithm (ACS) is prone to search stagnation and long planning time. To solve these issues, the randomness of initial search of the algorithm was reduced by improving the transition probability, adding the steering cost, and enhancing the path smoothness. Meanwhile, the pseudo-random state transition strategy was adjusted with adaptive parameters, and the pheromone update mode was improved to accelerate the algorithm convergence speed and find the global optimal solution. The results showed that the traditional ant colony optimisation (ACO) algorithm took 12 iterations and 2.02 s to obtain a path with a length of 65.32. The improved algorithm only needed four iterations and 0.12 s to lock the optimal path with length of 28.94. These results showed that the improved algorithm was superior to the conventional ACS, and its feasibility and effectiveness was verified. When the mobile robot searched for dynamic obstacles on the move, it could effectively avoid the temporary addition of static and dynamic obstacles and reach the target point. This study provides strong support for the efficient and safe navigation of mobile robots in complex environments.
Important Links:
Go Back
