FaceBots: Social robots utilizing facebook

Abstract

Although existing robotic systems are interesting to interact within the short term, it has been shown that after some weeks of quasi-regularencounters, humans gradually lose their interest, and meaningfullonger-term human-robot relationships are not established. An underlyinghypothesis driving the proposed project is that such relationshipscan be significantly enhanced if the human and the robot are graduallycreating a pool of shared episodic memories that they can co-referto, and if they are both embedded in a social web of other humansand robots they both know and encounter frequently. Thus, here wepropose to use Facebook, a highly successful online networking resourcefor humans, towards enhancing longer-term human-robot relationships,by helping to address the above two prerequisites. As a startingpoint, we utilize social information in order to personalize human-robotdialogues, and to include references to past encounters and to encounterswith friends within dialogues. A robot equipped with a modular softwarearchitecture (with IPC-intercommunicating modules for face recognition,a simple dialog system, a navigation subsystem, and a real-time Facebookconnection/local social database) has been deployed, and is encounteringhumans in the environment of our lab. An early demonstration of abasic form of such encounters is shown in the submitted video. Thesystem is expected to achieve two significant novelties: arguablybeing one of the first robots to be embedded in a social web, andbeing the first robot that can purposefully exploit and create socialinformation that is available online. Furthermore, it is expectedto provide empirical support for our main driving hypothesis, thatthe formation of shared episodic memories within a social web canlead to more meaningful long-term human-robot relationships.