The Tuna Swarm Optimization (TSO) algorithm is easy to have poor search accuracy and high path cost when used for threedimensional path planning of UAVs.Thereforean improved TSO algorithm is designed based on lens imaging oppositelearning mechanism.Firstlynonlinear weight coefficient updatingthe best and worst opposite learningand lens imaging opposite learning strategies are introduced to optimize the performance of the TSO algorithm and to improve its accuracy when approaching the optimal solution.Thena threat model with geomorphic constraints and performance constraints is establishedand the 3D path planning problem of UAV is converted into an optimization problem of cost function.The improved algorithm is used to iteratively solve the path planningand search for the optimalsafe and obstacleavoiding path with the minimum cost.Simulation results of path planning show thatthe improved algorithm effectively solves the premature convergence problemand its planned path is shorter with lower costand the planning efficiency is improved.