Robot person following (RPF) is a capability that supports many useful human-robot-interaction (HRI) applications of a mobile robot. However, existing solutions to person following often assume a full observation of the tracked person. As a consequence, they cannot track the person reliably under partial occlusion where the assumption of full observation is not satisfied. In this paper, we focus on the problem of robot person following under partial occlusion caused by a limited field of view of a monocular camera. Based on the key insight that it is possible to locate the target person when one or more of his/her joints are visible, we propose a method in which each visible joint contributes a location estimate of the followed person. Experiments show that, even under partial occlusion, the proposed method can still locate the person more reliably than the existing methods. In combination with this person location module, our RPF system achieves SOTA results in a public person following dataset. As well, the application of our method is demonstrated in real experiments on a mobile robot.

翻译：机器人行人跟随（RPF）是支持移动机器人诸多实用人机交互（HRI）应用的关键能力。然而，现有行人跟随解决方案通常假设对跟踪目标具有完整观测。因此当部分遮挡导致完整观测假设不成立时，这些方法无法可靠追踪行人。本文聚焦于单目相机有限视野造成的部分遮挡场景下机器人行人跟随问题。基于"当目标关节部分可见时仍可定位该行人"这一关键洞察，我们提出了一种方法——通过每个可见关节贡献对跟随目标的定位估计。实验表明，即使在部分遮挡条件下，该方法仍能比现有方法更可靠地定位行人。将该行人定位模块与我们的RPF系统结合后，在公开行人跟随数据集上取得了当前最优（SOTA）结果。此外，在移动机器人上的真实实验验证了本方法的实用性。