Abstract: In this study, an improved chimp optimization algorithm is proposed to facilitate the path planning of mobile robots in an intelligent storage environment. For this, the algorithm initializes the population by neighborhood search, improving the quality of the population. Consequently, the algorithm improves the adaptive convergence process via the cosine convergence factor and also improves the diversity of the population and global search ability. A distance heuristic factor is introduced to classify and weigh the population so as to avoid the local optimal problem caused by late search chaos. The introduction of this factor improves the local search and exploration ability of the algorithm. By using traveling salesman problem library (TSPLIB) standard example database, the improved algorithm is compared with several intelligent algorithms, such as the standard chimp optimization algorithm. Our experimental results show that the improved algorithm has better robustness, convergence precision, and optimization speed in comparison with the other studied algorithms. Moreover, the improved algorithm has good applicability, can effectively optimize the path of the warehouse mobile robot, and improve the working efficiency