Weight matrix-based improved ant colony path planning method

Abstract

The invention relates to a weight matrix-based improved ant colony path planning method. The weight matrix-based improved ant colony path planning method innovatively introduces the weight matrix intopath planning to improve the algorithm efficiency, optimize the values of initial pheromones and reasonably limit residual pheromones and path weights. The weight matrix-based improved ant colony path planning method can achieve humanized path planning according to practical application context and avoid repeated site visiting to acquire the shortest and optimal path, thereby greatly improving the practical operation efficiency.

Description

technical field [0001] The invention relates to the field of automatic navigation, in particular to an improved ant colony path planning method based on weight matrix. Background technique [0002] Modern industrial production puts forward higher requirements for automated production and logistics systems. Automated guided vehicles are referred to as AGV (Automated Guided Vehicles). It is one of the key equipment in smart factories and smart logistics systems. It can realize unmanned, economical, Efficient production management, and path planning is one of the key technologies of AGV intelligence. Path planning is to find the most collision-free path from the starting point to the focal point in the working space according to certain optimization criteria (such as the shortest path, the shortest time, etc.) in the environment of given obstacles. A better path planning algorithm can not only improve the efficiency of automated production, but also ensure the utilization rate...

AI Technical Summary

Problems solved by technology

[0003] For automatic production line workshops and logistics warehouses, there are currently many path planning methods, such as simulated annealing algorithm, artificial potential field method, neural network algorithm, genetic algorithm, particle swarm algorithm, Dijkstra algorithm, A* algorithm, Floyd algorithm, etc., but Some do not work well in practical applications

The simulated annealing algorithm is simple in description, flexible in use and high in operating efficiency, but has defects such as slow convergence speed and randomness, and related parameters have a great influence on the application process; the path planned by the artificial potential field method is smooth and safe, and the description is simple, but there are local optimizations The design of the gravitational field is the key to the successful application of the algorithm; the neural network algorithm has a good learning ability, but its poor generalization ability is its fatal weakness; the genetic algorithm is easy to combine with other algorithms and can give full play to its iterative advantages, but low computational efficiency; particle swarm optimization algorithm is easy to implement, has good robustness, and fast convergence speed, but it is easy to fall into local optimum; Dijkstra algorithm has high success rate and good robustness, but it has too many traversal nodes and low efficiency. The Achilles’ heel of large and complex path topology networks; the A* algorithm has fewer expansion nodes, is robust, and responds quickly to environmental information, but in practical applications it ignores the node restrictions brought about by the volume of the moving body itself; the Floyd algorithm is simple and effective, However, it has the disadvantages of high time complexity and is not suitable for calculating large amounts of data.

[0004] In the path planning methods of the prior art, there are often accumulated errors in the long-term operation of the single inertial positioning module, which leads to a continuous decline in positioning accuracy. Big problems, and the general intelligent optimization algorithm can not achieve better results

Images