无先验地图情况下人员跟随策略

Human-following strategy without prior map

中文关键词: 人员跟随机器人  人机协作  避障  移动机器人  路径规划

英文关键词: human-following robot  human-robot collaboration  obstacle avoidance  mobile robot  path planning

中文摘要:

      人员跟随任务是人机协作最基本的功能，它要求机器人可以识别定位目标人员，规划路径并避障．为了提高人员跟随任务在不同场景的适用性，人员跟随任务应当不依赖于先验地图．针对目标人员的识别定位，提出了一种融合相机、激光雷达和UWB基站数据的方法．对于路径规划和避障，提出了一种改进TEB算法．实验结果表明，所提目标人员识别定位方法可以在多个行人中识别出目标人员，判断目标人员是否丢失，并以20 Hz的频率发布目标人员的位置．相较于仅使用UWB定位的方法，定位误差减小了50.11%．相较于付勇的方法，有效定位数据增加了3.65%．改进TEB算法不依赖先验地图，可以有效地应对各种不利条件，例如存在较多障碍物、存在较多行人、目标人员被遮挡、目标人员超出机器人视野等情况．完整的实验视频可以在相关网站观看．

英文摘要:

      The human-following task is a fundamental function in human-robot collaboration. It requires a robot to recognize and locate a target person, plan a path and avoid obstacles. To enhance the applicability of the human-following task in various scenarios, the human-following task should not rely on a prior map. For the identification and localization of the target person, an approach is proposed, which integrates data from a camera, a LiDAR and a UWB anchor. For path planning and obstacle avoidance, a modified TEB algorithm is introduced. Experimental results demonstrate that the proposed target person identification and localization method can recognize the target person among multiple individuals, determine whether the target person is lost, and publish the target person′s position at a frequency of 20 Hz. Compared to the method in which only UWB is used to locate the target person, the localization error is reduced by 50.11%. Compared to the method proposed by Fu Yong, the effective localization data is increased by 3.65%. The modified TEB algorithm does not rely on a prior map. And it can effectively handle various challenging conditions, such as multiple obstacles, multiple individuals, the target person being occluded, and the target person moving out of the robot′s field of view. The complete experimental videos are available for viewing on some website.