为了解决小型地面移动机器人在野外环境中的回收问题,利用2维激光雷达进行环境感知与末端精确引导,设计并实现了一个自主回收系统.首先,提出一种自适应曲率滤波算法预先对雷达数据进行滤波处理.然后,在检测引导目标过程中,结合基于密度和最近邻度量方法对散乱的数据进行聚类,并且利用引导目标和辅助目标之间的几何结构约束进行目标检测与匹配.最后,采用基于影响层划分和候选方向评估的方法进行实时避障与最优行驶方向选择,对机器人进行精确引导,从而实现机器人的自主回收.在野外环境中对该自主回收系统进行验证,对自主回收系统中的若干环节分别进行实验分析.实验结果表明,该方法能够有效地实现小型地面移动机器人在野外环境中的自主回收. In order to solve the problem of recovery of small ground mobile robot in the field environment, a two-dimensional lidar is used for environment perception and precise guidance of the end, an autonomous recovery system is designed and implemented.Firstly, an adaptive curvature filtering algorithm is proposed to predict the radar data Then filter the scattered data in the process of detecting the guidance target by combining the density-based and nearest-neighbor metric methods, and use the geometric constraints between the guidance target and the auxiliary target to detect and match the target.Finally, Real-time obstacle avoidance and optimal driving direction selection based on influence layer classification and candidate direction evaluation are adopted to guide the robots accurately, so as to achieve the autonomous recovery of robots.The autorecycling system is verified in the field environment, The experimental results show that this method can effectively realize the autonomous recovery of small ground mobile robots in the field environment.