Teaching motion planning concepts to undergraduate students

Abstract

Motion planning is a central problem in robotics. Although it is an engaging topic for undergraduate students, it is difficult to teach, and as a result, the material is often only covered at an abstract level. Deep learning could be achieved by having students implement and test different algorithms. However, there is usually no time within a single class to have students completely implement several motion planning algorithms as they require the development of many lower-level data structures. We present an ongoing project to develop a teaching module for robotic motion planning centered around an integrated software environment. The module can be taught early in the undergraduate curriculum, after students have taken an introductory programming class.