Using tactile-exploration with the Unscented Kalman Filter for high precision on-line shape and pose estimation of a 3D workpiece


A common problem faced in robotic manipulation is developing techniques for accurate localisation and mapping of 3D objects. Many techniques already exist to aid in estimating the structure of the world using information from a robot’s sensors such as stereo cameras, time-of-flight or structured light. These sensors and techniques used for modelling can often be made accurate enough for most practical applications (such as picking-up an object). However, some applications require a higher degree of accuracy (sub-millimeter) that is difficult to achieve with the information available from these sensors. This paper proposes the use of tactile exploration to incrementally improve the accuracy of a prior 3D object model as the robot touches different parts of a workpiece. A modified Unscented Kalman Filter (UKF) has been developed to fuse the touch probe data with the existing model and refine it over time. The approach presented in this paper is intended for applications that require a high degree of accuracy and reliability (such as medical procedures) and as such, focuses on three primary requirements—accuracy, robustness and practicality.


robotic manipulation, 3D objects, localization, mapping, medical procedures, Unscented Kalman Filter (UKF)

This document is currently not available here.

Find in your library