In this paper, we propose an observer-based visual pursuit control integrating 3-dimensional target motion learning by Gaussian Process Regression (GPR). We consider a situation where a visual sensor equipped rigid body pursuits a target rigid body whose velocity is unknown, but dependent on the target's pose. We estimate the pose from visual information and propose a Gaussian Process (GP) model to predict the target velocity from the pose estimate. We analyze stability of the proposed control by showing that estimation and control errors are ultimately bounded with high probability. Finally, simulations illustrate the performance of the proposed control schemes even if the visual measurement is corrupted by noise.

This paper considers a pursuit control based on cooperative target motion estimation by robotic networks equipped with visual sensors. First, we propose a cooperative pursuit control law with a vision-based observer using visual sensor networks, called networked visual motion observer. Then, we learn position dependent target motion by a Gaussian process and integrate it within the proposed control law. Second, we show that all rigid bodies converge to desired relative poses when at least one robot can obtain visual information of the target. Furthermore, we prove that the total estimation and control error is ultimately bounded with high probability when integrating a GP model. Finally, we demonstrate the effectiveness of the proposed control law through simulations.

In this paper, we propose an observer-based visual pursuit control integrating three-dimensional target motion learning by Gaussian Process Regression (GPR). We consider a situation where a visual sensor equipped rigid body pursuits a target rigid body whose velocity is unknown but dependent on the target's pose. We estimate the pose from visual information and propose a Gaussian Process (GP) model to predict the target velocity from the pose estimate. We analyse stability of the proposed control by showing that estimation and control errors are ultimately bounded with high probability. Finally, simulations illustrate the performance of the proposed control schemes even if the visual measurement is corrupted by noise.

Order picking is one of the most expensive tasks in warehouses nowadays and at the same time one of the hardest to automate. Technical progress in automation technologies however allowed for first robotic products on fully automated picking in certain applications. This paper presents a mobile order picking robot for retail store or warehouse order fulfillment on typical packaged retail store items. This task is especially challenging due to the variety of items which need to be recognized and manipulated by the robot. Besides providing a comprehensive system overview the paper discusses the chosen techniques for textured object detection and manipulation in greater detail. The paper concludes with a general evaluation of the complete system and elaborates various potential avenues of further improvement.

We address in this letter the learning of unknown rigid body motions in the Special Euclidian Group SE(3) based on Gaussian Processes. A new covariance kernel for SE(3) is presented and proven to be a valid kernel for Gaussian Process Regression. The learning error of the proposed Gaussian Process model is extended to a highprobability statement on SE(3). We employ it in a visual pursuit scenario of a moving target with unknown velocity in 3D space. Our approach is validated in a simulated 3D environment in Unity, and shows significant better prediction accuracy than the most commonly used Gaussian kernel. When compared to other covariance kernels proposed on SE(3), its advantages are a natural extension of covering numbers to SE(3), that it is computationally more efficient, and that stability of target pursuit can be guaranteed without limiting the target rotational space to SO(2).