This paperproposes an improved sparrow search algorithm (ISSA) with multistrategy fusion to address the issues ofdependence on initialpopulation distribution, susceptibilityto localoptima, and reduced population diversityin the later stages of iteration in sparrow search algorithm (SSA) . Firstly, the population is initialized using Sobol sequencesto ensurethe diversityoftheinitialpopulation. Secondly, random reverselearning strategyand spiralforaging strategy are introduced to improve the discoverer position update formula and the joiner position update formula, respectively, to enhance the algorithm's globalsearch ability and abilitytojump outoflocaloptimalsolutions. Finally, introducing Cauchy variation to perturb sparrows that may fall into local optima. Nine standard test functions were selected forperformance testingin the experiment, and the results showed thatthe improved algorithm had a significant improvementin performance. Applying ISSA to Automated Guided Vehicle (AGV) path planning can achieve optimal values of 13.135 6, 28.834 5, and 44.364 9 in three map environments, respectively. The optimization ability and stability ofthe algorithm are significantlyimproved compared to the originalalgorithm.