Proceedings ArticleDOI
Real-time CAD model matching for mobile manipulation and grasping
Ulrich Klank,Dejan Pangercic,Radu Bogdan Rusu,Michael Beetz +3 more
- pp 290-296
Reads0
Chats0
TLDR
This paper proposes a 3D perception system architecture that can robustly fit CAD models in cluttered table setting scenes for the purpose of grasping with a mobile manipulator, and compares the system's performance and reliability with similar initiatives.Abstract:
Humanoid robotic assistants need capable and comprehensive perception systems that enable them to perform complex manipulation and grasping tasks. This requires the identification and recognition of supporting planes and objects in the world, together with their precise 6D poses. In this paper, we propose a 3D perception system architecture that can robustly fit CAD models in cluttered table setting scenes for the purpose of grasping with a mobile manipulator. Our approach uses a powerful combination of two different camera technologies, Time-Of-Flight (TOF) and RGB, to robustly segment the scene and extract object clusters. Using an a-priori database of object models we then perform a CAD matching in 2D camera images. We validate the proposed system in a number of experiments, and compare the system's performance and reliability with similar initiatives.read more
Citations
More filters
Journal ArticleDOI
KnowRob: A knowledge processing infrastructure for cognition-enabled robots
Moritz Tenorth,Michael Beetz +1 more
TL;DR: This article introduces the KnowRob knowledge processing system, a system specifically designed to provide autonomous robots with the knowledge needed for performing everyday manipulation tasks, and evaluates the system’s scalability and present different integrated experiments that show its versatility and comprehensiveness.
Proceedings ArticleDOI
Robotic roommates making pancakes
Michael Beetz,Ulrich Klank,Ingo Kresse,Alexis Maldonado,Lorenz Mösenlechner,Dejan Pangercic,Thomas Rühr,Moritz Tenorth +7 more
TL;DR: A recent public experiment that shows two robots making pancakes using web instructions and the potential of the underlying technologies as well as the research challenges raised by the experiment are discussed.
Journal ArticleDOI
Data-driven grasping
Corey Goldfeder,Peter K. Allen +1 more
TL;DR: A novel framework for a data driven grasp planner that indexes partial sensor data into a database of 3D models with known grasps and transfersgrasps from those models to novel objects is proposed.
Journal ArticleDOI
Combined 2D-3D categorization and classification for multimodal perception systems
TL;DR: The system employs a library of specialized perception routines that solve different, well-defined perceptual sub-tasks and can be combined into composite perceptual activities including the construction of an object model database, multimodal object classification, and object model reconstruction for grasping.
Journal ArticleDOI
Web-Enabled Robots
TL;DR: This article introduces several categories of Web sites that can serve as information sources and explains which kinds of information they provide and several information processing methods that can access these Web sites to provide robots with necessary knowledge for performing everyday manipulation tasks.
References
More filters
Journal ArticleDOI
Robotic Grasping of Novel Objects using Vision
TL;DR: This work considers the problem of grasping novel objects, specifically objects that are being seen for the first time through vision, and presents a learning algorithm that neither requires nor tries to build a 3-d model of the object.
OpenRAVE: A Planning Architecture for Autonomous Robotics
Rosen Diankov,James J. Kuffner +1 more
TL;DR: This work introduces an open-source cross-platform software architecture called OpenRAVE, the Open Robotics and Animation Virtual Environment, targeted for real-world autonomous robot applications, and includes a seamless integration of 3-D simulation, visualization, planning, scripting and control.
Journal ArticleDOI
Robust Pose Estimation from a Planar Target
Gerald Schweighofer,Axel Pinz +1 more
TL;DR: It is shown that pose ambiguities - two distinct local minima of the according error function - exist even for cases with wide angle lenses and close range targets, and a new algorithm for unique and robust pose estimation from a planar target is developed.
Proceedings ArticleDOI
Object recognition and full pose registration from a single image for robotic manipulation
TL;DR: This paper presents an approach for building metric 3D models of objects using local descriptors from several images, optimized to fit a set of calibrated training images, thus obtaining the best possible alignment between the 3D model and the real object.
Player 2.0: Toward a Practical Robot Programming Framework
TL;DR: This paper describes recent work on restructuring the Player robot device server into a system that more closely aligns with the idea of a robot framework, and describes the flexibility of the new system.