Assistive robots are emerging to address a social need due to changing demographic trends such as an ageing population. The main emphasis is to offer independence to those in need and to fill a potential labour gap in response to the increasing demand for caregiving. This paper presents work undertaken as part of a dressing task using a compliant robotic arm on a mannequin. Several strategies are explored on how to undertake this task with minimal complexity and a mix of sensors. A Vicon tracking system is used to determine the arm position of the mannequin for trajectory planning by means of waypoints. Methods of failure detection were explored through torque feedback and sensor tag data. A fixed vocabulary of recognised speech commands was implemented allowing the user to successfully correct detected dressing errors. This work indicates that low cost sensors and simple HRI strategies, without complex learning algorithms, could be used successfully in a robot assisted dressing task.

Abstract-Robot-assisted dressing is performed in close physical interaction with users who may have a wide range of physical characteristics and abilities. Design of user adaptive and personalized robots in this context is still indicating limited, or no consideration, of specific user-related issues. This paper describes the development of a multi-modal robotic system for a specific dressing scenario -putting on a shoe, where users' personalized inputs contribute to a much improved task success rate. We have developed: 1) user tracking, gesture recognition and posture recognition algorithms relying on images provided by a depth camera; 2) a shoe recognition algorithm from RGB and depth images; 3) speech recognition and text-to-speech algorithms implemented to allow verbal interaction between the robot and user. The interaction is further enhanced by calibrated recognition of the users' pointing gestures and adjusted robot's shoe delivery position. A series of shoe fitting experiments have been performed on two groups of users, with and without previous robot personalization, to assess how it affects the interaction performance. Our results show that the shoe fitting task with the personalized robot is completed in shorter time, with a smaller number of user commands and reduced workload.

No abstract