Using Retinanet to determine local graspability for a suction actuator

Using Retinanet to determine local graspability for a suction actuator

van Tilburg, Floris (TU Delft Mechanical, Maritime and Materials Engineering)

Hernández, Carlos (mentor)
Wisse, M. (mentor)
Kooij, J.F.P. (graduation committee)
Imre, M. (graduation committee)

Delft University of Technology

2021-08-26

Suction based robotic actuators have potential for the bin-picking industry, but are currently not usable due the needed speed, accuracy and ability to handle novel and adversarial objects. An evaluation of the state of the art grasp pipeline developed by Mahler et al. [1] for detecting grasps on novel objects lead us to split the problem of robotic grasp generation into a global and a local component. The state of the art solution had the ability to fill the role of global evaluator leaving a local evaluator to be developed. This local grasp evaluator was obtained by training a neural network on a suction based grasp dataset, which was created using a newly developed annotation tool. The proposed grasp pipeline obtained by combining these two showed a 95.27% pick success rate for a random setup and a 90.28% success rate for solely novel objects.

suction gripper
bin-picking
unknown objects
robot vision
deep learning

http://resolver.tudelft.nl/uuid:d9e2c738-87b0-4bd9-b56a-7dfe2008f162

Student theses

master thesis

© 2021 Floris van Tilburg