Shared control for assistive mobile robots based on vector fields

Abstract

Technologies such as Brain-Computer Interface (BCI) and Electromyography (EMG) allow people with limited mobility to interact with devices such as computers, home appliances and mobile robots. However, low cost BCI and EMG have not matured yet. Moreover, these technologies present relative low signal-to-noise ratio and classification accuracy. In case of employing BCI or EMG to manually control a mobile robot, a shared control must be inserted in the loop control to compensate misinterpreted commands. This paper presents a novel shared control approach based on vector fields for the manual navigation of assistive mobile robots. Unlike other approaches which take full control of the robot in certain situations, this technique allows full control to the user. Also, this approach reduces interventions to correct the navigation route caused by wrong classification of commands issued by the user. Results show that it is a simple, fast and effective technique.