A Worked-Out Experience in Programming Humanoid Robots via the Kinetography Laban

This chapter discusses the possibility of using Laban notation to program humanoid robots. Laban notation documents human movements by a sequence of symbols that express movements as defined in the physical space. We show, by reasoning around the simple action of “taking a ball”, the flexibility of the notation that is able to describe an action with different level of details, depending on the final objective of the notation. These characteristics make Laban notation suitable as a high level language and as a motion segmentation tool for humanoid robot programming and control. The main problem in robotics is to express actions that are defined and operate in the physical space in terms of robot motions that originate in the robot motor control space. This is the fundamental robotics issue of inversion. We will first show how symbols used by Laban to describe human gestures can be translated in terms of actions for the robot by using a framework called Stack of Tasks. We will then report on an experience tending to implement on a simulated humanoid platform the notation score of a “Tutting Dance” executed by a dancer. Once the whole movement has been implemented on the robot, it has been again notated by using Laban notation. The comparison between both scores shows that robot’s movements are slightly different from dancer’s ones. We then discuss about plausible origins of these differences.