A collaborative behavior-based approach for handling ambiguity, uncertainty, and vagueness in robot natural language interfaces |
| |
Authors: | Fangju Wang Shaidah Jusoh Simon X Yang |
| |
Affiliation: | aDepartment of Computing and Information Science, University of Guelph, Guelph, Ont., Canada N1G 2W1 bSchool of Engineering, University of Guelph, Guelph, Ont., Canada N1G 2W1 |
| |
Abstract: | Service robots are used by ordinary people in their houses and offices. For such users, a desirable way to communicate with robots is through natural language interfaces. So far, techniques for developing robot natural language interfaces are far from mature. A major challenge is handling ambiguity, uncertainty, and vagueness in parsing, object resolution, and vague natural language words. In this research, we develop a new approach called the collaborative behavior-based approach, in which behaviors of robots and behaviors of human users, as well as the changes of object states caused by the behaviors, are taken into consideration integratedly in processing natural language user instructions. In this paper, we analyze the special features of a human–robot interface that may affect language understanding, describe our approach that is designed based on the features, and present the implementation and some experimental results. |
| |
Keywords: | Robot Natural language interface Possibility theory |
本文献已被 ScienceDirect 等数据库收录! |
|