基于CMAC神经网络的机器人平面视觉跟踪

在手眼关系及摄像机模型完全未知的情况下，建立了眼在手上机器人平面视觉跟踪问题的非线性视觉映射模型，将图像特征空间和机器人工作空间紧密地联系起来。在此基础上，为将视觉跟踪问题转化为图像特征空间中的定位问题，设计了基于CMAC神经网络的视觉跟踪控制方案，并与PD控制器相并联构成视觉反馈控制。仿真结果表明该算法能完全消除稳态跟踪误差，具有很强的环境适应性，算法简单，易于实时实现。

2D robotic visual tracking based on CMAC neural network

In this paper, without explicit external and internal calibration, we propose a nonlinear visual mapping model for the eye - in - hand robotic visual tracking problem, which connects the image feature space with the robotic work space tightly. Moreover, a new visual control scheme based on CMAC neural network is designed, which is parallel to the PD controller, the visual tracking problem is converted into a servo problem in image feature space. Simulation results show that this method can drive the static tracking error to zero quickly and keep good robustness and adaptability at the same time. Additionally, the algorithm is very easy to be implemented with low computational complexity.