Abstract
The Amazon Robotics Challenge (ARC) is a robotics competition aimed to advance warehouse automation. One of the engineering challenges is making the system robust to and being able to handle a wide variety of objects, as would be the case in a real warehouse. In this paper, we shortly describe our system used in ARC featuring a method to obtain object grasp poses containing the location of the object as well as orientation for the grasp by using a convolutional neural network with an RGB-D image as input. Through our entry in ARC 2016, we show the effectiveness of our method and the robustness of our network model to a large variety of object types in dense and unstructured environments wherein occlusions are possible.
Eiichi Matsumoto and Masaki Saito contributed equally to the work.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A video showing our system in action is accessible via http://goo.gl/ZavxX1.
References
Correll, N., et al.: Analysis and observations from the first Amazon Picking Challenge. IEEE Trans. Autom. Sci. Eng. 15(1), 172–188 (2016)
Eppner, C., et al.: Lessons from the Amazon Picking Challenge: four aspects of building robotic systems. In: Proceedings of the Robotics: Science and Systems, University of Michigan, Ann Arbor, 18–22 June (2016)
Guo, D., et al.: Deep vision networks for real-time robotic grasp detection. Int. J. Adv. Robot. Syst. 14(1), 1–8 (2016)
He, K., et al.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the International Conference on Computer Vision, CentroParque Convention Center, Santiago, 11–18 December (2015)
Hernandez, C., et al.: Team delft’s robot winner of the Amazon Picking Challenge 2016. In: Behnke, S., Sheh, R., Sarıel, S., Lee, D. (eds.) RoboCup 2016: Robot World Cup XX. RoboCup 2016. Lecture Notes in Computer Science, vol. 9776. Springer, Cham (2017)
Lenz, I., et al.: Deep learning for detecting robotic grasps. Int. J. Robot. Res. 34, 705–724 (2015)
Levine, S., et al.: Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. Int. J. Robot. Res. 37, 421–436 (2017)
Nguyen, A., et al.: Detecting object affordances with convolutional neural networks. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Daejeon Convention Center, Daejeon, 9–14 October (2016)
Pfeiffer, T., et al.: Team PFN source code (2016). https://github.com/amazon-picking-challenge/team_pfn. Accessed 18 Aug 2016
Pinto, L., Gupta, A.: Supersizing self-supervision: learning to grasp from 50K tries and 700 robot hours. In: Proceedings of the IEEE International Conference on Robotics and Automation, Waterfront Congress Centre, Stockholm, 16–21 May (2016)
Schwarz, M., et al.: NimbRo picking: versatile part handling for warehouse automation. In: Proceedings of the IEEE International Conference on Robotics and Automation, Marina Bay Sands, Singapore, 29 May–3 June (2017)
Yang, J.: Object contour detection with a fully convolutional encoder–decoder network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Caesars Palace, Las Vegas, 26 June–1 July (2016)
Zeng, A., et al.: Multi-view self-supervised deep learning for 6D pose estimation in the Amazon Picking Challenge. In: Proceedings of the IEEE International Conference on Robotics and Automation, Marina Bay Sands, Singapore, 29 May–3 June (2017)
Acknowledgements
The authors would like to thank Tobias Pfeiffer, Taizan Yonetsuji, Yasunori Kamiya, Ryosuke Okuta, Keigo Kawaai, Daisuke Okanohara for their contribution and work done in the Amazon Robotics Challenge as part of Team PFN, and FANUC Corporation of Japan for providing the robotic arms and technical support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Matsumoto, E., Saito, M., Kume, A., Tan, J. (2020). End-to-End Learning of Object Grasp Poses in the Amazon Robotics Challenge. In: Causo, A., Durham, J., Hauser, K., Okada, K., Rodriguez, A. (eds) Advances on Robotic Item Picking. Springer, Cham. https://doi.org/10.1007/978-3-030-35679-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-35679-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-35678-1
Online ISBN: 978-3-030-35679-8
eBook Packages: EngineeringEngineering (R0)