A local user mapping architecture for social robots

Abstract

User detection, recognition, and tracking is at the heart of human-robot interaction, and yet, to date, no universal robust method exists for being aware of the people in a robot's surroundings. The present article imports into existing social robotic platforms different techniques, some of them classical, and other novel, for detecting, recognizing, and tracking human users. The outputs from the parallel execution of these algorithms are then merged, creating a modular, expandable, and fast architecture. This results in a local user mapping through fusion of multiple user recognition techniques. The different people detectors comply with a common interface called PeoplePoseList Publisher, while the people recognition algorithms meet an interface called PeoplePoseList Matcher. The fusion of all these different modules is based on the Unscented Kalman Filtering technique. Extensive benchmarks of the subcomponents and of the whole architecture demonstrate the validity and interest of all levels of the architecture. In addition, all the software and data sets generated in this work are freely available.

Vision-based people detection using depth information for social robots

“…The RLPD is a new homemade data set containing real data acquired from one of our social robots in the laboratory. 37 The actors used to collect data for this data set were engaged in a realistic HRI scenario in which one or several users interact naturally with the robot: addressing the robot, using gestures, respecting the proxemics distance, and so on. The ground truth user positions have been manually labeled in each of the 600þ frames.…”