Fusion of automation and teleoperation for person-following with mobile robots

摘要

Person-following has been the focus of significant amount of research in the field of robotics recently. It is believed that detecting, recognizing and following people is one of the required functionalities for most future robots who will be sharing environments with their human companions. Fully automating these functionalities is considered as a significant challenge in developing any person-following system. This leads research to focus mostly on this challenge and divert from other challenges that coexist. A natural person-following functionality consists of a number of tasks that are required to be implemented in the system. However, in more realistic life scenarios, not all the tasks required for person-following need to be automated. Instead, some of these tasks can be operated by a human operator. In this paper, a novel taxonomy for person-Following is introduced. The taxonomy presents all the tasks that are believed to exist in any person-following system. It also presents a number of likely cycles of tasks based on real life scenarios. Then, in order to provide a natural human-robot interaction means, fusion of automation and teleoperation for person-following is achieved by using TeleGaze. TeleGaze was previously developed by the authors as a means of natural human-robot interaction for teleoperation through eye gaze. The use of TeleGaze shows how all the tasks in person-following can be addressed and how to achieve a realistic fusion of automation and teleoperation.