Designing Social Interactions for Learning Personalized Knowledge in Service Robots

Shengchen Zhang, Xiaohua Sun


Service robots are required to effectively gather and utilize personalized knowledge in a working environment, especially through social interaction with their users. Existing works have shown the significant influence of interaction design on the efficiency, accuracy, and user experience of learning interactions. Designing social interaction for learning personalized knowledge poses new challenges for HRI designers, which signifies a need for designerly knowledge in the form of tools, methods, and effective patterns.

In this paper, we present a toolkit to help the design of social interaction with service robots for the learning of personalized knowledge, by informing designers of key challenges and potentially applicable patterns to help ideation. We discuss five key challenges for interactively learning personalized knowledge based on existing literature, and propose ten interaction design patterns that can be employed to help the ideation. We then present a preliminary evaluation of the toolkit through workshop sessions with HRI designers. Questionnaires and semi-structured interviews were used to gather feedback from the participants. The results show the ability of the toolkit for aiding ideation and its potential for flexible ways of use, and point towards future directions to improve and expand the toolkit.

Cite as

Zhang, S., Sun, X. (2022). Designing Social Interactions for Learning Personalized Knowledge in Service Robots. In: Kurosu, M. (eds) Human-Computer Interaction. Technological Innovation. HCII 2022. Lecture Notes in Computer Science, vol 13303. Springer, Cham. https://doi.org/10.1007/978-3-031-05409-9_47

Source code (Github)