A Review of Service Robots Coping With Uncertain Information in Natural Language Instructions

Intelligent service robots are currently being developed to cater to demands in emerging areas of robotic applications, ranging from entertainment to health care. These service robots are intended to be operated by nonexpert users, and their service tasks involve direct interaction between these robots and their human users. Thus, human-friendly interactive features are generally preferred for such service robots. Humans prefer to use voice instructions, responses, and suggestions to convey ideas to their peers. However, information conveyed through natural language communication is imprecise because it tends to contain uncertain/qualitative information instead of precise quantitative information. Therefore, the ability to cope with uncertain information in natural language instructions is mandatory for human-friendly service robots. This paper presents a review of service robots and systems that can cope with uncertain information in natural language instructions. The available literature has been investigated and analyzed to identify the limitations of the existing methods and possible improvements. The identified limitations and possible improvements are presented as the outcomes of the review.