Development of Intelligent Behaviors for Social Robots via User-Friendly and Modular Programming Tools

Abstract

The expected adoption of robots able to interact with people in real-world scenarios brings the need to move from easy-to-use to easy-to-develop robot architectures. In this paper, we discuss how a component-based methodology, a block and web-based interface, and a behavior tree approach to the development of robot behaviors can be used together to enable the adoption of the end-user development (EUD) paradigm. The proposed framework (i) mainly uses easy-to-install, cross-platform and modular tools, (ii) is ROS, ZeroMQ and nanomsg compatible, (iii) enables the creation of platform-independent applications, and (iv) can be easily expanded with new sensory devices or robots. In order to evaluate the proposed software framework, an example of a human-robot interaction application using a NAO robot is presented and discussed.