Nao Robot Navigation System Structure Development in an Agent-Based Architecture of the RAPP Platform

Abstract

This paper focuses on the development of a navigation system structure for the Nao humanoid robot in an agent-oriented distributed architecture. The proposed navigation system is a part of the RAPP framework, a cloud based robotics platform. The RAPP framework is an open-source software platform to support the creation and delivery of robotic applications, which are expected to increase the versatility and utility of robots. All navigation tasks are defined and divided into separate components. The robot navigation system consists of a relative localisation based on Extended Kalman Filter (EKF) using both IMU and odometry measurements, visual QR-code based global localization, path planning, and motion control components. A proper allocation of navigation components, in the four-agent structure of the RAPP platform, is the main goal of this work. Navigation system components are implemented using Robot Operating System and Nao robot programming framework—NAOqi. Experimental results for the Nao robot are presented to show the validity of the proposed approach.