Communication through movement: An alternative method of interaction for HRI

Abstract

Human-robot interaction (HRI) often relies on audio and visual channels for communication between robots and human users. While these methods have proven to be successful, the reliance on these two channels limits their effectiveness in extreme environments and for people with certain disabilities. In this paper, we present an alternative communication method in which users manipulate the robot's arm as a form of input while also using the arm for output. This haptic interaction enables users to give inputs while maintaining contact with the arm, and in turn helps visually impaired users by avoiding the need to search for other interaction elements of the robot. As the user moves the robot's arm around, resistance is generated to guide user movements. The system learns user-defined gestures using SVM and is able to classify subsequent gestures and their associated user intentions. We demonstrate that the system can learn and classify different gestures by conducting a preliminary exploration with four users. Different configurations and gestures are further discussed to demonstrate the scalability of the system to different robotic platforms. We also discuss scenarios that benefit from simultaneous physical input and output across a wide range of communities, thus illustrating a step towards a universal design method for physical HRI.