Name
Title | ||
|---|---|---|
Tracking, reconstruction and grasping of unknown rotationally symmetrical objects from a conveyor belt |
Abstract | ||
|---|---|---|
Many manipulation applications in industrial settings using robots depend on reliable detection and grasping capabilities of stationary or moving objects. The latter demand an extended use of intrinsic and extrinsic sensors being in a closed control-loop with a robotic system. In this paper we present an approach for tracking, reconstruction and grasping of unknown objects from a moving conveyor belt using an external depth sensor and an industrial robot. The approach consists of an algorithm for the estimation of the position, velocity and form of an object, an algorithm for estimation of the conveyor's path and an algorithm for calculating an interception trajectory for the robot. The presented scheme is designed for tracking and reconstruction of unknown rotationally symmetrical objects. Nevertheless, the reconstruction algorithm is able to detect asymmetrical parts of an object and recognize if an object is hollow. This is further used for calculation of a feasible grasp. From the reconstruction data a mesh of the object is created. Finally, robots interception and grasping trajectory are calculated on-line for any arbitrary position on the conveyor. The objects are sucessfully grasped from moving conveyor up to the speed of more than 10 [cm/s]. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/ETFA.2017.8247651 | 2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) |
Keywords | Field | DocType |
robotic system,moving conveyor belt,external depth sensor,industrial robot,unknown rotationally symmetrical objects,reconstruction algorithm,robots interception,grasping trajectory,manipulation applications,industrial settings,reliable detection,reconstruction data,closed control-loop,extrinsic sensors,intrinsic sensors,grasping capabilities | Interception,Conveyor belt,Robotic systems,Computer vision,GRASP,Real-time computing,Industrial robot,Reconstruction algorithm,Artificial intelligence,Engineering,Robot,Trajectory | Conference |
ISSN | ISBN | Citations |
1946-0740 | 978-1-5090-6506-6 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Denis Stogl | 1 | 13 | 2.46 |
| Daniel Zumkeller | 2 | 0 | 0.34 |
| Stefan Escaida Navarro | 3 | 42 | 6.32 |
| Alexander Heilig | 4 | 0 | 0.68 |
| Björn Hein | 5 | 39 | 12.36 |