Research On Dynamic Routing And Obstacle Avoidance Optimization Path Planning For Intelligent Driving Vehicles

With the development of technology and social progress,intelligent driving vehicles are increasingly widely used in various fields.In order to optimize the dynamic path finding and obstacle avoidance path of intelligent driving vehicles,the following research has been mainly conducted in this paper:(1)This paper divides vehicle path planning into two stages: global static and local dynamic,and then combines the algorithms used in the two stages to achieve global dynamic vehicle path planning.The experimental results show that the method studied in this topic can plan a path that meets the requirements for vehicles,enable vehicles to achieve dynamic routing and avoid obstacles,and can improve the efficiency of path planning.(2)For static path planning,most algorithms have shortcomings such as weak optimization ability,easy to fall into local optimization,and slow convergence speed.Therefore,this paper proposes two improved optimization algorithms: In the first improved algorithm,the Grey Wolf optimization algorithm and genetic algorithm are combined.During the iteration process,the wolf pack is evolved and updated to improve the convergence speed of the algorithm.Experimental results show that the fusion algorithm can not only plan a path that meets the requirements,but also has a fast convergence speed and improved search efficiency.In the second improved algorithm,based on the whale optimization algorithm,this paper adds an adaptive dynamic adjustment mechanism to dynamically adjust the search behavior,introduces a controllable variable to coordinate the global optimization and local optimization of the algorithm,and combines a differential evolution strategy to further update the position of the whale individuals after each iteration of the algorithm.Experimental results show that the improved whale optimization algorithm has greatly improved solution quality,stability,and efficiency compared to other swarm intelligence algorithms.(3)For local dynamic planning,this paper conducts a secondary processing of the global path,and extracts the key nodes in the path after the static path planning algorithm solves the global path.Then,an improved dynamic window algorithm is applied to perform local dynamic path planning,so that the vehicle can be optimized when passing through key nodes during driving.Experimental results show that the algorithm used in this paper not only improves the efficiency of dynamic path planning,but also makes the vehicle’s driving path smoother,and can achieve the functions of global dynamic vehicle routing and obstacle avoidance.In summary,the two improved algorithms proposed in this paper can improve the efficiency of path planning and improve the quality,stability,and speed of solution in global static path planning.The reprocessing of global static paths extracts key nodes,simplifies the path,and improves the efficiency of vehicle travel.Finally,combined with an improved dynamic window algorithm,the vehicle’s global dynamic obstacle avoidance path is optimized.