The automated guided vehicle (AGV) with sensor recognition method is having shortcomings such as high cost and noise. In this regard, the flower pollination algorithm (FPA) is applied in the path detection system of an AGV, in combination with computer vision. The path detection system starts with image acquisition using an onboard camera. The captured image is then preprocessed to obtain simple contrast of the path. Subsequently, the FPA is used to find a set of solution points fall inside the path zone. A regression model is formed as path guidance for AGV to travel accordingly. The performance of FPA is analyzed via simulation and real-world experiment using a robotic platform and tested on commonly seen line patterns in the industrial environment. The effectiveness of FPA in path detection is also compared with particle swarm optimization. The obtained results demonstrate the promising feasibility of the proposed FPA-based path detection system.

采用传感器识别方法的自动导引车（AGV）存在成本高、噪声大等缺点。对此，花授粉算法（FPA）结合计算机视觉应用于AGV路径检测系统。路径检测系统从使用车载摄像头获取图像开始。然后对捕获的图像进行预处理以获得路径的简单对比度。随后，FPA 用于找到一组落在路径区域内的解点。形成回归模型作为AGV相应行驶的路径引导。FPA 的性能通过使用机器人平台的模拟和真实世界实验进行分析，并在工业环境中常见的线条图案上进行测试。还将 FPA 在路径检测中的有效性与粒子群优化进行了比较。