Research On Obstacle Avoidance And Path Optimization Algorithm Of Intelligent Car

Nowadays,many airlines are promoting mobile robot technology to shorten downtime,reduce inspection and maintenance costs.Wheeled unmanned car is a good choice for airlines.This paper studies the path planning and obstacle avoidance of intelligent automobile,and tries to create a free path for the unmanned vehicles to travel through the working space.An improved genetic algorithm is proposed for global path planning under a known environment to obtain a feasible and effective path from the starting point to the target point.The algorithm modifies the traditional genetic algorithm.Particle swarm optimization algorithm is used to reconstruct the mutation operator,to avoid premature convergence,and the fitness function was modified to improve the speed of the algorithm.At the same time,in order to solve a large number of infeasible paths due to crossover and mutation,a repair mechanism is added to study the infeasible path,and then repair it.When the local environment is unknown,an improved dynamic window approach is proposed for local path planning.The improved dynamic window approach modifies the cost function to reduce the negative effects.At the same time,the modified cost function is smoothed to make the cost function more reliable.Finally,the improved genetic algorithm and the improved dynamic window approach are integrated into the path planning of the intelligent automobile,so that the intelligent automobile can normally achieve the expected goal in the dynamic uncertain environment.Through MATLAB’s static and dynamic simulation,as well as autonomous obstacle avoidance experiments of the intelligent automobile,the effectiveness and practicality of the method are verified.The method is not only vital for the path planning and obstacle avoidance of the intelligent automobile,but also has theoretical reference value for path planning of other types of robots.