Sensing, Intelligence, Motion: How Robots and Humans Move in an Unstructured World

CHAPTER 5

Motion, Planning for Two-Dimensional Arm Manipulators

If we imagine constructions to be made with rigid rods … we should find that different laws hold for these from those resulting on the basis of Euclidean plane geometry. The surface is not a Euclidean continuum with respect to the rods, and we cannot define Cartesian co-ordinates in the surface.

–Albert Einstein,Relativity: The Special and General Theory

5.1 INTRODUCTION

In Chapter 3 we have developed the foundations of the SIM (Sensing–Intelligence–Motion) paradigm (called also sensor-based robot motion planning). Basic algorithms were developed for the simplest case of a point robot that possesses tactile sensing and operates in a two-dimensional scene populated with obstacles of arbitrary shapes. The algorithms were then extended to richer sensing such as vision, as well as to algorithm versions that take into account robot dynamics. When the robot starts on its journey, it knows nothing about the shapes, locations, and number of individual obstacles in the scene. It acquires information about its surroundings from its sensors—much the way we humans see and listen and smell when moving in the physical world. The robot's only goal is to arrive at its target location. This means that when it arrives there, it may still know very little about the scene. In other words, knowing more about the scene is not the objective. ...