Research On Path Planning Of Warehouse Robots Based On Intelligent Algorithm

With the rapid development of the logistics industry in our country,warehousing robots are becoming more and more common.The existing warehousing robots can only complete relatively simple tasks,easy to appear the path for a long time,etc.,which is not enough to deal with the complex warehousing environment at present.Therefore,this paper designs different path planning algorithms for different storage environments,so that the storage robot can find the optimal path in the shortest time.The details are as follows:Aiming at the path planning of traditional stacking warehouse,the Cartesian coordinate system method is used for modeling.To solve the problems of local extremum and slow convergence in path planning based on particle swarm optimization(PSO),a directional optimization particle swarm optimization algorithm based on obstacle distribution is proposed in this paper.Firstly,the optimal space is generated according to the distribution of obstacles,then the optimal space particles are introduced into the velocity iteration formula of the algorithm,which improves the ability of the algorithm to jump out of local extremum.Then an adaptive time-varying strategy is used to dynamically adjust the learning factors to speed up the convergence.Finally,the effectiveness of the algorithm is verified by comparing with PSO and PSO-HJ algorithm through MATLAB simulation experiment.The results show that the proposed algorithm accelerates the convergence speed and improves the ability of jumping out of local extremum.In order to solve the problems of long running time,low searching efficiency and frequent deadlock in the path planning of ant colony algorithm,this paper proposes an ant colony algorithm based on Darwin’s theory of evolution.Firstly,a simple mode of ant colony algorithm is proposed to solve the problem of blind search in blank grid;secondly,in order to improve the global search ability of the algorithm and avoid falling into deadlock,the target influence factor and obstacle influence factor are introduced into the heuristic function;finally,the pheromone updating rules of ant colony algorithm are improved by using Darwin’s theory of evolution to accelerate the iteration speed and shorten the running time of the algorithm.Experiments on raster maps of different scales show that the evolutionary ant colony algorithm proposed in this paper speeds up the iteration speed,improves the search efficiency,achieves the optimal path and avoids the deadlock problem.In order to solve the problems of searching resource waste,deadlock and non-optimal path planning of multi-robot in warehouse environment,a fusion algorithm is proposed.Firstly,particle swarm optimization(PSO)is used to optimize the main parameters of the ant colony algorithm,which improves the search performance of ant colony algorithm(ACO).Secondly,a feasible multi robot obstacle avoidance strategy is proposed to make the path planning meet the obstacle avoidance requirements in the storage environment.Thirdly,aiming at the deadlock problem and non-optimal problem caused by the narrow corridor and semi enclosed terrain in the warehouse,the fast traffic strategy and virtual objective method are further proposed.Finally,ant colony algorithm(ACO)and slime mold algorithm(SMA)are fused to solve the problem of resource waste.Compared with other algorithms,the proposed algorithm is superior to other algorithms in path length,number of deadlocked ants and runtime.