ABSTRACT
A time-of-flight (ToF) camera is a relatively new type of sensor that delivers three-dimensional images at high frame rate, simultaneously providing intensity data and range information for every pixel. This chapter describes the lessons learned by using such cameras to perform robotic tasks, specifically in eye-in-hand configurations. Eye-in-hand configurations have been used extensively for object modeling and enable robot interaction with the environment. The chapter aims to introduce ToF cameras and presents a critical comparison with RGBD cameras, a different 3D sensor that is more and more commonly used in robotics. ToF cameras have been used to sense relatively large depth values for mapping or obstacle avoidance in mobile robotics, and also for human detection and interaction. The chapter reviews systematic and nonsystematic error sources. It shows that the combination of both ToF and color images to obtain colored point clouds.
