Project Description
Abstract
Recent advances in robot control and safety systems al- lowed the access, in the last few years, of robots in our daily life. Robotic systems have been applied to several fields, such as social assistance, surveillance, tour-guide or floor cleaning. These contexts are very different from traditional industrial applications, in which robots are typically utilized by expert users. In fact, in daily life applications, users are typically inexperienced, and do not have any specific education related to robot programming: the design of effective human-robot interaction systems is then of paramount importance, for these applications.
To enable non-expert users to interact with robots, natural user interfaces have been recently developed. The main idea is that of allowing a direct expression of mental concepts by intuitively mimicking real-world behavior. NUIs offer a natural and reality-based interaction by exploiting users’ pre-existing knowledge and using actions that correspond to daily practices in the physical world. To achieve this, natural interfaces allow users to directly manipulate objects and interact with robots rather than instruct them to do so by typing commands.
In particular, we have been studying a novel hands-free infrastructure-less natural interface for HRI, based on the recognition of the movements of user’s forearm. The interface is based on the use of an everyday multipurpose device, such as a commercial smartwatch, which provides the user with freedom of movement and let her/him be immersed in the environment where the robot moves. The movements of the user’s forearm are detected and translated into velocity commands for the robot; moreover, gestures are recognized to provide high-level commands. Such an interaction system is general and can be applied to any robot and multi-robot system. Specifically, we have considered its use with wheeled mobile robots and quadrotors.
The usability of such natural interface has been assessed in different conditions, and compared to standard interaction systems, such as joystick, haptic device, and smartphone. The achieved results have proved the effectiveness and intuitiveness of such an interaction approach.

