luation of model-based tracking and its application in a robotic production line

Abstract

The assessment of the accuracy and stability of model-based tracking approaches in the literature is a challenging task. Many of the presented methods lack a detailed evaluation or comparison to accurate ground truth data. Considering real world applications, it is hard to estimate the applicability of the respective method. In this paper we present methods to evaluate the accuracy and stability of model-based tracking approaches. Thereby, we focus on an industrial use and the robustness of the approach considering error sources like the influence of lighting over time, noise and the mechanical camera setup in general. The second part of this paper deals with the evaluation and application of model-based tracking in a robotic production line for gap measurements in the automotive industry. We present a method for synchronization with a conveyor setup and an operating robot. In this complex setup various error sources influence the output accuracy of the system. A further accuracy evaluation method is presented that uses the robot as a measurement device of the total error. The paper closes with the application of a model-based tracking system for robotic measurement tasks in a production line.