Collecting User's Responses To Test Action In Active Robot Learning Based On Pressure Senor Array Model

In recent years, service robots have been increasingly used in people's daily life, such as homecare, healthcare, rescue assistant, tour guide, etc. It is important to address cooperation between a robot and its users. In the process of cooperation between service robots and human, how to enable service robots to understand their user's intention is a hot topic in research today, based on the understanding, the robots can coordinate and adjust their behaviors to provide desired assistance and services to the users as capable partners. Active robot learning (ARL) is an approach to the development of beliefs for the robots on their users'intention and preference, which is needed by the robots to facilitate the seamless cooperation with users. This approach allows a robot to perform tests on its users and to build up the high-order beliefs according to the users'responses. This study carried out primary research on designing a pressure sensor array model for attaching to the robot's finger tips to collect the user's responses to test action in ARL system. Firstly, this research shows development of service robots, several methods for collecting user's intention and ARL. Then, Mathematics model and the reference value threshold which decides the feature of pressure distribution were proposed through a benchmark scenario experiment. The robot holds an object and presents it to the user. When the user does not take over the object, the pressure distribution on the robot's finger tip shown on pressure sensor array model is uneven. When user takes over the object, the pressure distribution on the robot's finger tip is even. According to the relationship between the pressure distributions with user's responses, the user's responses to test action can be recognized by the robot. Finally, two episodes of a benchmark scenario which is the robot passing an object to the user is simulated in a simulation software, GraspIt, in this study. The simulation results proved the developed pressure sensor array model can successfully collect the user's responses to test action in ARL...