Research On Application Of Improved Ant Colony Algorithm In Intelligent Car Path Planning

With the rapid development of robot-related technologies,mobile robots represented by smart cars have been widely used in transportation,industrial engineering,aviation and education.Nowadays,the research results in the field of mobile robots can be seen as a measure of the level of technological development of a country in the direction of robot research to a certain extent.In the study of smart car-related technologies,one of the key technologies is path planning.Compared with traditional path planning methods,the current smart car path planning method is developing towards autonomy and intelligence.Stable,accurate,and fast path planning algorithms have become an important part of smart car path planning research.Given that the basic ant colony algorithm has a strong advantage in path planning,after studying the basic ant colony algorithm path planning technology,this paper makes related improvements and then applies it to the smart car platform based on the Arduino control board.The main research contents are as follows:Firstly,through studying and analyzing of the current status of path planning algorithms,the basic ant colony algorithm with strong robustness is selected and applied to the path planning of smart cars.Because the basic ant colony algorithm is prone to stagnation,slow convergence,and local optimal solutions,etc.,this paper designed an improved ant colony algorithm.Firstly,by adaptively changing the volatilization coefficient,this strategy enhances the ant colony search ability at the initial moment and expands its scope,the purpose is to effectively avoid falling into the local optimal solution.The operator is added to it,which effectively improves the quality of understanding and the convergence speed of the algorithm.Finally,through elite selection or better path node cross-operation,the global search efficiency and convergence speed of the algorithm are effectively improved.Next,the improved ant colony algorithm is applied to the TSP problem and path planning respectively.Experimental simulations show that the improved ant colony algorithm in this paper not only improves the convergence speed of the algorithm,but also improves the security of the path.Secondly,when solving the obstacle problem in the dynamic environment,the global path was obtained by using the improved ant colony algorithm firstly.Then,when the smart car encounters the dynamic obstacle,it must first determine the type of collisions that is about to occur,whether it is a frontal collision or a side collision,and corresponding collision strategy was used to achieve successful obstacle avoidance for dynamic obstacles.Finally,A four-wheel smart car hardware platform based on the Arduino control board was built.During the experiments,the smart car was used to avoid static and dynamic obstacles,thus the experiment verified the effectiveness and real-time of the improved ant colony algorithm.