基于人工免疫算法的图像直接反馈视觉伺服

提出了一种基于图像直接反馈的平面视觉伺服控制方法，其特点是不需要提取期望图像与反馈图像的图像特征而用人工免疫的智能进化算法直接求解期望图像与反馈图像之间的位置与夹角误差向量，再将此误差信号经视觉控制器转换成机器人空间的位姿增量信号发送给机器人控制器，从而完成视觉伺服闭环控制。与传统的基于图像特征的视觉伺服控制方法相比具有更好的通用性与稳定性。对算法的关键技术、实现步骤及参数选择进行了深入分析，并通过实验验证了所提方法的有效性与稳定性。

A Visual Servoing Method Using Direct Image Feedback and Artificial Immune Algorithm

A novel visual servoing method is proposed for a robot with a camera in the hand to track an object by direct image feedback without image features acquirement, where an artificial immune algorithm is designed to get the error vector between the reference image and the feedback image.Because of using all the image information and without image features acquirement, the better universality and stability can be realized based on the technology in this paper. Then the key technology, algorithm procedure and the parameters choosing are analyzed in detail; The experiment results show that the method is valid and practicable.