Applicat Ion Of Improved Ant Colony Algorithm In Robot Path Planning

With the development and progress of Artificial Intelligence technology in today's society,the application of Artificial Intelligence in life and production expends gradually and attract more and more researchers into it.Artificial Intelligence has become a hot research hotspot in today's life.Artificial intelligence research branch of many,intelligent robot research is an important research direction in the field and has been paid more and more attention with the continuous progress of technology.In order to improve the efficiency of the robot to complete the task,we hope that the robot can have the function of independent security pathfinder.Often,path planning is not just about the task of finding the path from the beginning to the end,but should also be able to screen out a short,time-consuming,and safe path on a number of viable paths to improve work effectiveness.In recent years,on the issue of path planning,experts and scholars at home and abroad have given their own solution to their problems,and have obtained good results in their respective problem models,including genetic algorithm,particle swarm optimization,artificial immune algorithm,Neural network method,artificial field method and so on.In many application algorithms,the ant colony algorithm has been widely concerned since its introduction.This thesis mainly describes the research and improvement of the algorithm based on the ant colony algorithm under the research of mobile robot path planning.The main work of the thesis are as follows:1.This thesis discusses the idea and implementation steps of ant colony algorithm systematically.The advantages and disadvantages.of the ant colony algorithm in the path planning problem are analyzed from the concept of the classical ant colony algorithm.Ant colony algorithm uses the means of bionic,according to the ant in the process of foraging road behavior,through the post-generation feedback information,and gradually converges to get the global optimal path,has the advantages of strong robustness.But also have a long search time,easy to fall into the local convergence of the problem.2.This thesis lists the improvement and optimization of ant colony algorithm by many scholars,some of them are to make improvements in the algorithm based on the classical ant colony algorithm,and some make the ant colony algorithm combined with other algorithms,learn from each other to make the ant colony algorithm increasingly optimized.Different improvement strategies have been a good effect in the corresponding application scenario;the introductory part of this thesis analyzes and discusses these improvements.The main innovations presented in this thesis are as follows:1.This thesis presents an improved algorithm for the problem that the classical ant colony algorithm has a slow convergence rate and easy to fall into the local optimal problem in the robot path planning problem under complex environment.According to the direction guidance information,the distribution of the initial pheromone is optimized,the search speed is accelerated,and the time consumption of the search is reduced.By optimizing the pheromone evaporation and updating rules,the advantages of local and global excellent paths are preserved and the convergence rate is improved.Based on regional security factors to improve the transfer probability,so as to avoid falling into the local optimal and deadlock and other issues.In order to verify the effectiveness of the improvement,two-dimensional modeling of the simulation environment through the grid method is carried out to simulate the maps with different complexity and scale.2.An improved ant colony algorithm is proposed for multi-objective programming with path cost.Based on the initial pheromone distribution rules mentioned above,the path cost factor is added to provide the direction of the original ants.According to the characteristics of multi-objective planning,a strategy of ant colony division is proposed,which gives different groups of different tasks to the multi-target planning.In addition,in the distribution of pheromone,according to the different ant colony task set different rules,and then through the transition probability optimization choice,in the simulation experiment has come to a good result.