PDF(Pubmed)
Abstract：
This study introduces a novel approach for enhancing robotic path planning and navigation by optimizing point configuration through convolutional neural networks (CNNs). Faced with the challenge of precise area coverage and the inefficiency of traditional traversal and intelligent algorithms (e.g., genetic algorithms, particle swarm optimization) in point layout, we proposed a CNN-based optimization model. This model not only tackles the issues of speed and accuracy in point configuration with Gaussian distribution characteristics but also significantly improves the robot\'s capability to efficiently navigate and cover designated areas with high precision. Our methodology begins with defining a coverage index, followed by an optimization model that integrates polygon image features with the variability of Gaussian distribution. The proposed CNN model is trained with datasets generated from systematic point configurations, which then predicts optimal layouts for enhanced navigation. Our method achieves an experimental result error of <8% on the test dataset. The results validate effectiveness of the proposed model in achieving efficient and accurate path planning for robotic systems.
摘要：
本研究介绍了一种通过卷积神经网络（CNN）优化点配置来增强机器人路径规划和导航的新方法。面对精确区域覆盖的挑战以及传统遍历和智能算法的低效率（例如，遗传算法，粒子群优化)在点布局中，提出了一种基于CNN的优化模型。该模型不仅解决了具有高斯分布特征的点配置中的速度和准确性问题，而且显着提高了机器人高效导航和高精度覆盖指定区域的能力。我们的方法从定义覆盖指数开始，然后是一个优化模型，该模型将多边形图像特征与高斯分布的可变性集成在一起。所提出的CNN模型使用从系统点配置生成的数据集进行训练，然后预测增强导航的最佳布局。我们的方法在测试数据集上实现了<8%的实验结果误差。结果验证了该模型在实现机器人系统高效、准确的路径规划方面的有效性。
