Enhancing User Satisfaction by Adapting Robot's Perception of Uncertain Information Based on Environment and User Feedback

Assistive robots have been developed to improve the living standards of older people. These assistive robots are intended to be operated by non-expert users. Hence, they should have the ability to interact with humans in a human-friendly manner. Humans prefer to use voice instructions, responses, and suggestions in their daily interactions. Such voice instructions and responses often include uncertain terms and lexical symbols rather than precise quantitative values. Therefore, the ability of robots to understand uncertain information is a crucial factor in the implementation of human-friendly interactive features in robots. This paper proposes a novel method of adapting the perception of the uncertain spatial information contents of navigational commands, such as "far'' and "little'', based on environmental factors and user feedback. The proposed uncertain information understanding module has been implemented using fuzzy neural networks in such a way that the system can concurrently adapt to environmental factors while learning from user feedback. The proposed method has been implemented on the MIRob platform, and experiments have been conducted in an artificially created domestic environment to evaluate the performance and behaviors of the proposed concept. The experimental results validate the improvement of user satisfaction related to the understanding of uncertain information.