Zhang Jiawei
Beijing Normal University - Hong Kong Baptist University United International College, Zhuhai, 519000, Guangdong, China.
Sci Rep. 2025 Apr 26;15(1):14656. doi: 10.1038/s41598-025-93926-1.
This paper aims to solve the challenges faced by intelligent robots in navigation and path planning, and proposes a method combining fuzzy neural network (FNN) and genetic algorithm (GA). This method first uses the fuzzy neural network algorithm to improve the navigation accuracy of the robot in a complex environment; secondly, the genetic algorithm is used to optimize the efficiency of path planning to ensure that the robot can complete navigation in the shortest time. The study compares the navigation methods that integrate BP neural network (BPNN), self-organizing map network (SOM) and adaptive resonance theory neural network (ART). The experimental results show that the navigation accuracy of the intelligent robot based on the fuzzy neural network algorithm is as high as 98.64%, the shortest navigation time is 9.64s, and the minimum error angle deviation is 1.52%. The intelligent robot based on the FNN and GA algorithm model spends the shortest time in path planning and has the highest efficiency, which has strongly promoted the further development of the field of intelligent robots.
本文旨在解决智能机器人在导航和路径规划中面临的挑战，并提出一种将模糊神经网络（FNN）和遗传算法（GA）相结合的方法。该方法首先利用模糊神经网络算法提高机器人在复杂环境中的导航精度；其次，利用遗传算法优化路径规划效率，确保机器人能在最短时间内完成导航。该研究比较了集成BP神经网络（BPNN）、自组织映射网络（SOM）和自适应共振理论神经网络（ART）的导航方法。实验结果表明，基于模糊神经网络算法的智能机器人导航精度高达98.64%，最短导航时间为9.64秒，最小误差角度偏差为1.52%。基于FNN和GA算法模型的智能机器人在路径规划中花费时间最短，效率最高，有力地推动了智能机器人领域的进一步发展。
