Aiming at the shortcomings of the parrot optimization(PO)algorithm in solving optimization problems

such as slow convergence speed and susceptibility to local optimization

a multi-strategy fusion parrot optimization(MFPO)algorithm is proposed.The algorithm employs Logistic chaotic map and opposition-based learning to initialize the population

enhancing population diversity and uniformity.An adaptive weight factor is used as a tuning parameter to balance global exploration and local optimization.Hybrid Cauchy-Gaussian mutation is applied for position updates

improving the algorithm’s global exploration capability in the early stage and local convergence capability in the later stage to prevent it from getting stuck in local optima.To validate the effectiveness of the MFPO algorithm

several standard test functions are selected as experimental benchmarks.The results indicate that the MFPO algorithm exhibits better convergence and convergence rates compared to other optimization algorithms.Finally

the MFPO algorithm is applied to robot path planning problem

where it outperforms the comparison algorithms in all metrics

verifying the effectiveness and engineering practicality of the improved algorithm MFPO.