Traditional industrial robots have been widely used in automotive manufacturing for nearly 30 years. However, there have been very few attempts to automate mobile robotic systems for final assembly operations, despite their potential for high flexibility and capability. This paper focuses on methods of tracking a dynamic moving vehicle that is similar to the vehicle body on a moving assembly line. We have investigated two tracking methods, one using a laser scanner and the other using a visual fiducial marker. We have also studied the tracking performance of a mobile base using the pure pursuit algorithm with low pass filtering. Experimental results are presented to illustrate the remaining main challenges in achieving robotic assembly on moving assembly lines.

Artificial skin research has focused on three primary characteristics: high density, flexible sensing arrays, and the ability to decompose all three components of an applied force vector. Previous research has accomplished some but not all of these characteristics. In this paper, we present a new flexible, high density sensor array and a triaxial force discernment algorithm that can be used with commercially available flexible high density sensor arrays. Together, the sensing array and algorithm achieve all three of the critical skin characteristics. With an addition of thin silicone pillar arrays, the triaxial force discernment algorithm provides a direct solution for nearly all possible force directions. Where the solution is ambiguous, our algorithm is able to reduce the uncertainty to a small range of known values. To confirm the validity of the algorithm, a testbed for a single sensing element was developed. Initial results show a resolution of less than 0.01 radians and calculated force components within the uncertainty of the ground truth for most situations. Our approach opens doors for many applications including robotic manipulation, haptic interfaces, human-robot interaction, and medical diagnoses

In this paper, we study the relationship between multi-view active appearance model (AAM) fitting and camera calibration. In the first part of the paper we propose an algorithm to calibrate the relative orientation of a set of N > 1 cameras by fitting an AAM to sets of N images. In essence, we use the human face as a (non-rigid) calibration grid. Our algorithm calibrates a set of 2 /spl times/ 3 weak-perspective camera projection matrices, protections of the world coordinate system origin into the images, depths of the world coordinate system origin, and focal lengths. We demonstrate that the performance of this algorithm is comparable to a standard algorithm using a calibration grid. In the second part of the paper, we show how calibrating the cameras improves tile performance of multi-view AAM fitting.