[HSR] Person Following Robot with Active Target Search
This work addresses a framework for person-following robots using active search. The proposed system is applied to the Toyota Human Support Robot to general person-following policies by learning features of people for detecting and tracking. To succeed at person- following, perception, planning, and robot behavior are integrated. An active searching process, including prediction and navigation toward vantage locations for finding people, is used. The proposed capability aims at improving the robustness and efficiency for tracking and following people under dynamic conditions such as crowded environments. A link to the paper can be found at: http://arxiv.org/abs/1809.08793