Learn

OpenCourseWare for AI-Focused Service Robotics

OpenCourseWare for AI-Focused Service Robotics

RoboCup@Home has been the largest international annual competition for autonomous service robots as part of the RoboCup initiative. It has greatly fostered artificial intelligence development in various robotics domains. However, the development of such service robots requires exclusively high amount of technical knowledge and resources. RoboCup@Home Education is an educational initiative that promotes service robot development. Under this initiative, a new educational challenge was initiated in RoboCup Japan Open since 2015. An educational Open Robot Platform is developed to assist new teams to develop service robots. The educational efforts are extended via various outreach programs, including domestic workshops and international academic exchange programs.

The purpose of this work is to enhance the educational efforts by having an OpenCourseWare based on the Open Robot Platform development for the learning of service robot development. The area of technical fields involved to build a service robot covers a wide spectrum of robotics research domains, including mobile robot navigation, computer vision and perception for object recognition, robot arm manipulation, speech recognition, and human-robot interaction. The OpenCourseWare is developed to be a hands-on (project-based learning) course to learn service robotics by building the robot. Based on the current robot development documentation, a series of online courseware is designed and developed for the education of service robot development. The courseware contents include course syllabus, lecture notes, online tutorials and videos, hardware development and software programming assignments, and project-based exams. Based on the project-based learning approach, the exams of the courseware involve the evaluation of the developed basic service robot functionalities based on the specifications of RoboCup@Home tasks. RoboCup@Home provides a quantitative scoring system to evaluate and benchmark the robot performance.

This work is mainly supported by IEEE RAS CEMRA (Creation of Educational Material in Robotics and Automation) Project.

The course contents are developed partially in collaboration with MathWorks. All contents are open source.