Robot person following (RPF) is a crucial capability in human-robot interaction (HRI) applications, allowing a robot to persistently follow a designated person. In practical RPF scenarios, the person often be occluded by other objects or people. Consequently, it is necessary to re-identify the person when he/she re-appears within the robot's field of view. Previous person re-identification (ReID) approaches to person following rely on offline-trained features and short-term experiences. Such an approach i) has a limited capacity to generalize across scenarios; and ii) often fails to re-identify the person when his re-appearance is out of the learned domain represented by the short-term experiences. Based on this observation, in this work, we propose a ReID framework for RPF that leverages long-term experiences. The experiences are maintained by a loss-guided keyframe selection strategy, to enable online continual learning of the appearance model. Our experiments demonstrate that even in the presence of severe appearance changes and distractions from visually similar people, the proposed method can still re-identify the person more accurately than the state-of-the-art methods.

翻译：机器人跟随人员（RPF）是人机交互（HRI）应用中的关键能力，可使机器人持续跟随指定人员。在实际RPF场景中，目标人员常被其他物体或人群遮挡。因此，当该人员重新出现在机器人视野中时，需要对其进行重识别。现有用于人员跟随的行人重识别（ReID）方法依赖离线训练的特征和短期经验。这类方法存在以下问题：i）跨场景泛化能力有限；ii）当目标人员重新出现时的外观超出短期经验所代表的学习域时，往往无法成功重识别。基于此观察，本文提出一种利用长期经验的RPF ReID框架。该框架通过损失引导的关键帧选择策略维护长期经验，从而实现外观模型的在线持续学习。实验表明，即使存在严重的外观变化和来自视觉相似人员的干扰，所提方法仍能比现有最优方法更准确地完成人员重识别。