12:00, 19 Feb 1997, WeH 7220 Socially Embedded Learning of Office-Conversant Mobile Robot "Jijo-2" Hideki ASOH Senior Researcher Jijo-2 Project Team Electrotechnical Laboratory In my talk I will describe an exploration into a newly developing direction of machine learning, called ``socially embedded learning''. In this research we have been building an office-conversant mobile robot which autonomously moves around in an office environment, actively gathers information through close interaction with environment including sensing multi-modal data and making dialog with people in the office, acquires knowledge about the environment, and finally becomes conversant with its environment. Here our major concern is in how the close interaction between the learning system and its environmental society can help or accelerate the system's learning process, what kinds of prepared mechanisms are necessary for the emergence of such interactions. The office-conversant robot is a platform to implement ideas and to test their feasibility in a real-world setting. Overview of the system and two examples of implemented ideas, dialog-based map acquisition and route acquisition by following, will be demonstrated.