This paper presents ViKi-HyCo (Visual servoing and Kinematic Hybrid-Controller), an approach that generates the necessary maneuvers for the complex positioning of a non-holonomic mobile robot in outdoor environments, towards a target point based on the object detection, by combining an image based visual servoing (IBVS) and a kinematic controller. The method avoids the problems of the visual servoing controller when it loses the visual object detection features by switching to a kinematic controller. We also present object localization for outdoor environments employing the fusion of LiDAR and RGB-D cameras that estimates the spatial location of a target point for the kinematic controller, and also allows the dynamic calculation of a desired bounding box of the detected object for the calculation of velocities in the visual servoing controller. The presented approach does not require an object tracking algorithm and is applicable to any visually tracking robotic task where its kinematic model is known. The Hybrid-Control presents an error of 0.0428 \pm 0.0467 m in the X-axis and 0.0515 \pm 0.0323 m in the Y-axis at the end of a complete positioning task.

翻译：本文提出ViKi-HyCo（视觉伺服与运动学混合控制器）方法，该方法通过融合基于图像的视觉伺服（IBVS）与运动学控制器，基于目标检测生成非完整移动机器人在室外环境中向目标点定位所需的机动操作。该方法通过切换至运动学控制器，规避了视觉伺服控制器在丢失视觉检测特征时出现的问题。我们同时提出一种融合LiDAR与RGB-D相机的室外环境目标定位方法，该方法既能估算运动学控制器所需目标点的空间位置，也能动态计算检测目标的期望边界框，用于视觉伺服控制器中的速度计算。该方法无需目标跟踪算法，适用于任何已知运动学模型的视觉跟踪机器人任务。完整定位任务结束时，该混合控制方法在X轴和Y轴上的误差分别为0.0428±0.0467米和0.0515±0.0323米。