TY - JOUR A1 - Berscheid, Lars A1 - Meißner, Pascal A1 - Kröger, Torsten T1 - Self-supervised Learning for Precise Pick-and-place without Object Model JF - IEEE Robotics and Automation Letters (RA-L) 5 (3) N2 - Flexible pick-and-place is a fundamental yet challenging task within robotics, in particular due to the need of an object model for a simple target pose definition. In this work, the robot instead learns to pick-and-place objects using planar manipulation according to a single, demonstrated goal state. Our primary contribution lies within combining robot learning of primitives, commonly estimated by fully-convolutional neural networks, with one-shot imitation learning. Therefore, we define the place reward as a contrastive loss between real-world measurements and a task-specific noise distribution. Furthermore, we design our system to learn in a self-supervised manner, enabling real-world experiments with up to 25000 pick-and-place actions. Then, our robot is able to place trained objects with an average placement error of 2.7 (0.2) mm and 2.6 (0.8)°. As our approach does not require an object model, the robot is able to generalize to unknown objects while keeping a precision of 5.9 (1.1) mm and 4.1 (1.2)°. We further show a range of emerging behaviors: The robot naturally learns to select the correct object in the presence of multiple object types, precisely inserts objects within a peg game, picks screws out of dense clutter, and infers multiple pick-and-place actions from a single goal state. Y1 - 2020 U6 - https://doi.org/10.1109/LRA.2020.3003865 ER - TY - JOUR A1 - Meißner, Pascal A1 - Schmidt-Rohr, Sven R. A1 - Lösch, Martin A1 - Jäkel, Rainer A1 - Dillmann, Rüdiger T1 - Localization of furniture parts by integrating range and intensity data robust against depths with low signal-to-noise ratio JF - Robotics and Autonomous Systems N2 - In this article we present an approach for localizing planar parts of furniture in depth data from range cameras. It estimates both their six-degree-of-freedom poses and their dimensions. The system has been designed for enabling robots to autonomously manipulate furniture. Range cameras are a promising sensor category for this application. As many of them provide data with considerable noise and distortions, detecting objects, for example, using canonical methods for range data segmentation or feature extraction, is complicated. In contrast, our approach is able to overcome these issues. This is done by combining concepts of 2D and 3D computer vision as well as integrating intensity and range information in multiple steps of our processing chain. Therefore it can be employed on range sensors with both low and high signal-to-noise ratios and in particular on time-of-flight cameras. This concept can be adapted to various object shapes. It has been implemented for object parts with shapes similar to ellipses as a proof-of-concept. For this, a state-of-the-art ellipse detection method has been enhanced regarding our application. Y1 - 2014 U6 - https://doi.org/10.1016/j.robot.2012.07.018 VL - 62 IS - 1 SP - 25 EP - 37 ER - TY - JOUR A1 - Meißner, Pascal A1 - Dillmann, Rüdiger T1 - Implicit Shape Model Trees - Recognition of 3-D Indoor Scenes and Prediction of Object Poses for Mobile Robots JF - robotics N2 - This article describes an approach for mobile robots to identify scenes in configurations of objects spread across dense environments. This identification is enabled by intertwining the robotic object search and the scene recognition on already detected objects. We proposed “Implicit Shape Model (ISM) trees” as a scene model to solve these two tasks together. This article presents novel algorithms for ISM trees to recognize scenes and predict object poses. For us, scenes are sets of objects, some of which are interrelated by 3D spatial relations. Yet, many false positives may occur when using single ISMs to recognize scenes. We developed ISM trees, which is a hierarchical model of multiple interconnected ISMs, to remedy this. In this article, we contribute a recognition algorithm that allows the use of these trees for recognizing scenes. ISM trees should be generated from human demonstrations of object configurations. Since a suitable algorithm was unavailable, we created an algorithm for generating ISM trees. In previous work, we integrated the object search and scene recognition into an active vision approach that we called “Active Scene Recognition”. An efficient algorithm was unavailable to make their integration using predicted object poses effective. Physical experiments in this article show that the new algorithm we have contributed overcomes this problem. Y1 - 2023 U6 - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:863-opus-53649 VL - 12 IS - 158 PB - MDPI ER - TY - JOUR A1 - Holomjova, Valerija A1 - Starkey, Andrew J A1 - Yun, Bruno A1 - Meißner, Pascal T1 - One-shot learning for task-oriented grasping JF - IEEE Robotics and Automation Letters Y1 - 2023 U6 - https://doi.org/10.1109/LRA.2023.3326001 VL - 8 IS - 12 SP - 8232 EP - 8238 ER -