Conditional WGAN for grasp generation

Patzelt F, Haschke R, Ritter H (2019)
In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN).

Konferenzbeitrag | Englisch
 
Download
Es wurde kein Volltext hochgeladen. Nur Publikationsnachweis!
Abstract / Bemerkung
This work proposes a new approach to robotic grasping exploiting conditional Wasserstein generative adversarial networks (WGANs), which output promising grasp candidates from depth image inputs. In contrast to discriminative models, the WGAN approach enables deliberative navigation in the set of feasible grasps and thus allows a smooth integration with other motion planning tools. We find that the training autonomously partitioned the space of feasible grasps into several regions corresponding to different grasp types. Each region forms a smooth grasp manifold with latent parameters corresponding to important grasp parameters like approach direction. We evaluate the model in simulation on the multi-fingered Shadow Robot hand, comparing it a) to a classical grasp planner for primitive geometric object shapes and b) to a state-of-the-art discriminative network model. The proposed generative model matches the grasp success rate of its trainer models and exhibits better generalization.
Erscheinungsjahr
2019
Titel des Konferenzbandes
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)
Konferenz
ESANN 2019
Konferenzort
Bruges, Belgium
Page URI
https://pub.uni-bielefeld.de/record/2935541

Zitieren

Patzelt F, Haschke R, Ritter H. Conditional WGAN for grasp generation. In: European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). 2019.
Patzelt, F., Haschke, R., & Ritter, H. (2019). Conditional WGAN for grasp generation. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN)
Patzelt, F., Haschke, R., and Ritter, H. (2019). “Conditional WGAN for grasp generation” in European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN).
Patzelt, F., Haschke, R., & Ritter, H., 2019. Conditional WGAN for grasp generation. In European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN).
F. Patzelt, R. Haschke, and H. Ritter, “Conditional WGAN for grasp generation”, European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), 2019.
Patzelt, F., Haschke, R., Ritter, H.: Conditional WGAN for grasp generation. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). (2019).
Patzelt, Florian, Haschke, Robert, and Ritter, Helge. “Conditional WGAN for grasp generation”. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN). 2019.

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar