Objective To enhance the operational stability of food sorting robots and the efficiency of time-optimal trajectory planning.Methods A time-optimal trajectory planning method for food sorting robots based on an improved beaver algorithm (BA) is proposed. First, with the six-degree-of-freedom robotic arm of the sorting robot as the research object, a time-optimal constrained optimization model based on 4-5-4 polynomial interpolation is established. Secondly, the BA is improved by introducing adaptive beaver species classification, population spatial directional evolution, and global jump strategy, effectively balancing the global exploration breadth and local search fineness of the algorithm. The improved BA is then applied to the optimization model of robotic arm joint trajectory planning. Finally, the MATLAB simulation platform and a physical platform built for egg sorting are employed to verify the feasibility of the proposed method.Results The proposed method reduces the running time by 5.67%~10.49%, and the error between the test results of the experimental platform and the simulation results is below 2.0%, verifying the feasibility of stable operation in the real environment.Conclusion The proposed method can significantly reduce the trajectory running time of food sorting robots.