Tutorial: Social Interaction with Cloud Network Robots

Tutorial: Social Interaction with Cloud Network Robots

14th International Conference on Intelligent Environments (IE'18) 25-28 of June 2018, Rome - Italy http://www.intenv.org/


Now we obtain capabilities to access ubiquitous information spaces and our human ability and cognitive performance will be gradually enhanced. Robots will also be integrated well into the human life and helping us naturally. They will have rich sensory perception and expressive facial signals, and are going to be social partners for us. In this tutorial, we will discuss what kind of “sociality” robots should have in human robot interactions (HRI).

“Making Robots More Acceptable” -- the words of Professor Gordon Chen who leads ICS (Institute for Cognitive System) at TUM. What exactly is a robot that does not give discomfort to us and we can easily accept its existence as a part of everyday life?
Being human, the behaviors with “sociality” will have an important meaning. Like communication skill to understand or sympathize with others, skill to recognize multiple contexts at the same time correctly and skill to create moderate intervals with interaction partners, ability to ensure social performance is various. Robots, and even everyday things, are also similar. An information system or a robot which has advanced interpersonal communication skill, can show correct judgement in all circumstances and be able to cooperate with people, robots, everyday things and various information services, such existence is probably an “acceptable” information system or robot.

Robots are interactive interfaces in real-world between users and ubiquitous information services. If the robot technology advances and many of objects in our everyday life are robotized, the cooperative world with such novel things “next generation IoT” will be opened. In this tutorial, robots and IoT devices which provide a certain kind of sociality are called “Sociable Robots” and “Sociable Things”.

Robots that work as an edge terminals of cloud services are called a “Cloud Network Robots”. The architecture of the Cloud Network Robots which realizes cooperative operations among heterogeneous robots can be the base of Sociable Robots and Sociable Things. A wide variety of robots aim at achieving their goals while sharing information on services that each can provide, autonomously and adaptively forming communities corresponding to tasks they are faced with, and working together with various cloud services. Some of them will coexist with us as actors of ubiquitous and cloud information services and some will argument our human ability by making full use of M2M (Machine to Machine) communication and M2S (Machine to Service) communication.

The Cloud Network Robots are beginning to be implemented in various forms such as agent software on information devices like smart phones, communication robots, and personal mobility robots such as wheelchairs and EV vehicles. The technical issues of Cloud Network Robot are as follows:

  • Cooperation and collaboration technologies among heterogeneous robots
  • Data linkage technologies between robot and cloud information service
  • Many-to-many human robot interaction technologies

In addition to these issues, in this tutorial, we will discuss the following two more issues for Sociable Robots:

  • Highly accurate perceptual processing and context recognition technologies for HRI
  • Social and affective interaction technologies in HRI


From the viewpoint of the sociality, the perception and context capturing function possessed by robots themselves is an important factor in determining behaviors of robots in human interactions. In this tutorial, we will focus attention on the emotional recognition of the communication partner, that is, the acquisition mechanism of human’s emotional changes, which is indispensable for realizing “social and emotional interaction”, and will exemplify its principles, implementation methods, and application examples. The lecturer has exemplified many-to-many human robot interactions in various usage scenes by implementing “sympathizing robot”, “remote ice breaking robot system”, etc. Topics covered in this tutorial range over “pseudo-emotional behaviors of robot in HRI”, “the personality of robot naturally being built by HRI”, “creating moderate interval and proximity in HRI” and so on. They are examples of next generation social and emotional human robot interactions.

Topics of interest

  1. Cloud Network Robotics
    • Robots active at the edge of services
    • Raising robots with cloud AI
    • Creating robot community
    • The changes in human robot interaction
  2. Robots who began to have Physical Characteristics:
    • Robot design in first person viewpoint
    • Understanding what’s going on around itself
    • Understanding the partner’s emotions and intentions
    • Robot that began to have feelings
    • Can people sympathize with robots?
  3. Robots acting Social - Sociable Robots
    • Eleven requirements for sociality
    • Understanding the flow of conversation - conversation context management
    • Management the interval and the proximity in HRI
    • Interaction fosters robot’s personality
    • Robots supporting human to human communication
    • Practice in the nursing care field


Kazunori Takashio Professor at Faculty of Environment and Information Studies Graduate School of Media and Governance - Keio University

Kazunori Takashio is a professor in the Faculty of Environment and Information Studies at Keio University, Japan. He received his Ph.D. in computer science from Keio University. He specializes in cloud network robotics, human robot interaction and ubiquitous computing. His research interests include real-time distributed systems, software robots, sociable robot system and affective human robot interaction. He is a member of ACM, IEEE and Information Processing Society of Japan (IPSJ), and a vice chair of Technical Committee on Cloud Network Robotics in The Institute of Electronics, Information and Communication Engineers (IEICE).