Transferring Human Navigational Skills to Smart Wheelchair
This chapter presents a case study in which human navigational skills are transferred to a wheelchair. It describes a novel environment modeling approach by explicit local range sensing and provides an experimental study is presented to show the feasibility of the approach and the corresponding results. The chapter explores the feasibility and performance of the approach on the navigation and localization applications are the foci. The environments in which mobile robots operate are usually modeled in highly complex forms, and as a result autonomous navigation and localization can be difficult. The paradigm of learning-by-demonstration has attracted some attention for its ability to solve navigation problems. Local environments, in which the robot is situated, are represented in the form of range sensor signals for pattern recognition during autonomous navigation or localization. Some interpretations can be drawn for illustrating the characteristics of the approach for navigation application.