Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Pseudo-Labeling and Contextual Curriculum Learning for Online Grasp Learning in Robotic Bin Picking (2403.02495v1)

Published 4 Mar 2024 in cs.RO and cs.AI

Abstract: The prevailing grasp prediction methods predominantly rely on offline learning, overlooking the dynamic grasp learning that occurs during real-time adaptation to novel picking scenarios. These scenarios may involve previously unseen objects, variations in camera perspectives, and bin configurations, among other factors. In this paper, we introduce a novel approach, SSL-ConvSAC, that combines semi-supervised learning and reinforcement learning for online grasp learning. By treating pixels with reward feedback as labeled data and others as unlabeled, it efficiently exploits unlabeled data to enhance learning. In addition, we address the imbalance between labeled and unlabeled data by proposing a contextual curriculum-based method. We ablate the proposed approach on real-world evaluation data and demonstrate promise for improving online grasp learning on bin picking tasks using a physical 7-DoF Franka Emika robot arm with a suction gripper. Video: https://youtu.be/OAro5pg8I9U

Definition Search Book Streamline Icon: https://streamlinehq.com
References (41)
  1. J. Bohg, A. Morales, T. Asfour, and D. Kragic, “Data-driven grasp synthesis—a survey,” IEEE Transactions on robotics, vol. 30, no. 2, pp. 289–309, 2013.
  2. K. Kleeberger, R. Bormann, W. Kraus, and M. F. Huber, “A survey on learning-based robotic grasping,” Current Robotics Reports, vol. 1, no. 4, pp. 239–249, 2020.
  3. R. Newbury, M. Gu, L. Chumbley, A. Mousavian, C. Eppner, J. Leitner, J. Bohg, A. Morales, T. Asfour, D. Kragic, et al., “Deep learning approaches to grasp synthesis: A review,” IEEE Transactions on Robotics, 2023.
  4. M. Danielczuk, A. Balakrishna, D. S. Brown, S. Devgon, and K. Goldberg, “Exploratory grasping: Asymptotically optimal algorithms for grasping challenging polyhedral objects,” arXiv preprint arXiv:2011.05632, 2020.
  5. L. Fu, M. Danielczuk, A. Balakrishna, D. S. Brown, J. Ichnowski, E. Solowjow, and K. Goldberg, “Legs: Learning efficient grasp sets for exploratory grasping,” in 2022 International Conference on Robotics and Automation (ICRA).   IEEE, 2022, pp. 8259–8265.
  6. A. Zeng, S. Song, S. Welker, J. Lee, A. Rodriguez, and T. Funkhouser, “Learning synergies between pushing and grasping with self-supervised deep reinforcement learning,” 2018.
  7. L. Berscheid, P. Meißner, and T. Kröger, “Robot learning of shifting objects for grasping in cluttered environments,” in 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019, Macau, SAR, China, November 3-8, 2019.   IEEE, 2019, pp. 612–618.
  8. L. Berscheid, C. Friedrich, and T. Kröger, “Robot learning of 6 dof grasping using model-based adaptive primitives,” in IEEE International Conference on Robotics and Automation, ICRA 2021, Xi’an, China, May 30 - June 5, 2021.   IEEE, 2021, pp. 4474–4480.
  9. Z. Feldman, H. Ziesche, N. A. Vien, and D. D. Castro, “A hybrid approach for learning to shift and grasp with elaborate motion primitives,” in International Conference on Robotics and Automation (ICRA).   IEEE Press, 2022, p. 6365–6371.
  10. W. Zhou, B. Jiang, F. Yang, C. Paxton, and D. Held, “Learning hybrid actor-critic maps for 6d non-prehensile manipulation,” CoRR, vol. abs/2305.03942, 2023. [Online]. Available: https://doi.org/10.48550/arXiv.2305.03942
  11. K. Sohn, D. Berthelot, N. Carlini, Z. Zhang, H. Zhang, C. A. Raffel, E. D. Cubuk, A. Kurakin, and C.-L. Li, “Fixmatch: Simplifying semi-supervised learning with consistency and confidence,” Advances in neural information processing systems, vol. 33, pp. 596–608, 2020.
  12. B. Zhang, Y. Wang, W. Hou, H. Wu, J. Wang, M. Okumura, and T. Shinozaki, “Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling,” Advances in Neural Information Processing Systems, vol. 34, pp. 18 408–18 419, 2021.
  13. J. Mahler, F. T. Pokorny, B. Hou, M. Roderick, M. Laskey, M. Aubry, K. Kohlhoff, T. Kröger, J. Kuffner, and K. Goldberg, “Dex-net 1.0: A cloud-based network of 3d objects for robust grasp planning using a multi-armed bandit model with correlated rewards,” in IEEE International Conference on Robotics and Automation (ICRA), 2016, pp. 1957–1964.
  14. A. Zeng, S. Song, K.-T. Yu, E. Donlon, F. R. Hogan, M. Bauza, D. Ma, O. Taylor, M. Liu, E. Romo, et al., “Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching,” IJRR, vol. 41, no. 7, pp. 690–705, 2022.
  15. D. Morrison, J. Leitner, and P. Corke, “Closing the loop for robotic grasping: A real-time, generative grasp synthesis approach,” in RSS XIV, Pittsburgh, USA, 2018.
  16. V. Satish, J. Mahler, and K. Goldberg, “On-policy dataset synthesis for learning robot grasping policies using fully convolutional deep networks,” RA-L, vol. 4, no. 2, pp. 1357–1364, 2019.
  17. H.-S. Fang, C. Wang, M. Gou, and C. Lu, “Graspnet-1billion: A large-scale benchmark for general object grasping,” in IEEE CVPR, 2020, pp. 11 444–11 453.
  18. M. Sundermeyer, A. Mousavian, R. Triebel, and D. Fox, “Contact-graspnet: Efficient 6-dof grasp generation in cluttered scenes,” in 2021 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2021, pp. 13 438–13 444.
  19. H. Cao, H.-S. Fang, W. Liu, and C. Lu, “Suctionnet-1billion: A large-scale benchmark for suction grasping,” IEEE RA-L, vol. 6, no. 4, pp. 8718–8725, 2021.
  20. P. Schillinger, M. Gabriel, A. Kuss, H. Ziesche, and N. A. Vien, “Model-free grasping with multi-suction cup grippers for robotic bin picking,” CoRR, vol. abs/2307.16488, 2023.
  21. J. Kober, J. A. Bagnell, and J. Peters, “Reinforcement learning in robotics: A survey,” International Journal of Robotics Research, vol. 32, no. 11, pp. 1238–1274, 2013.
  22. D. Kalashnikov, A. Irpan, P. Pastor, J. Ibarz, A. Herzog, E. Jang, D. Quillen, E. Holly, M. Kalakrishnan, V. Vanhoucke, and S. Levine, “Qt-opt: Scalable deep reinforcement learning for vision-based robotic manipulation.” in The Conference on Robot Learning (CoRL), vol. abs/1806.10293, 2018.
  23. S. Levine, P. Pastor, A. Krizhevsky, J. Ibarz, and D. Quillen, “Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection,” The International journal of robotics research, vol. 37, no. 4-5, pp. 421–436, 2018.
  24. A. Bicchi and V. Kumar, “Robotic grasping and contact: a review,” in IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065), vol. 1, 2000, pp. 348–353 vol.1.
  25. P. Schmidt, N. Vahrenkamp, M. Wächter, and T. Asfour, “Grasping of unknown objects using deep convolutional neural networks based on depth images,” in 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018, pp. 6831–6838.
  26. H. Y. Li, M. Danielczuk, A. Balakrishna, V. Satish, and K. Goldberg, “Accelerating grasp exploration by leveraging learned priors,” in 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE).   IEEE, 2020, pp. 110–117.
  27. M. Laskey, J. Mahler, Z. McCarthy, F. T. Pokorny, S. Patil, J. Van Den Berg, D. Kragic, P. Abbeel, and K. Goldberg, “Multi-armed bandit models for 2d grasp planning with uncertainty,” in 2015 IEEE International Conference on Automation Science and Engineering (CASE).   IEEE, 2015, pp. 572–579.
  28. Y. Shi, P. Schillinger, M. Gabriel, A. Kuss, Z. Feldman, H. Ziesche, and N. A. Vien, “Uncertainty-driven exploration strategies for online grasp learning,” 2023.
  29. X. Zhu, D. Wang, O. Biza, G. Su, R. Walters, and R. Platt, “Sample efficient grasp learning using equivariant models,” Proceedings of Robotics: Science and Systems (RSS), 2022.
  30. Y. Wang, H. Chen, Q. Heng, W. Hou, M. Savvides, T. Shinozaki, B. Raj, Z. Wu, and J. Wang, “Freematch: Self-adaptive thresholding for semi-supervised learning,” ArXiv, vol. abs/2205.07246, 2022. [Online]. Available: https://api.semanticscholar.org/CorpusID:248811614
  31. H. Chen, R. Tao, Y. Fan, Y. Wang, J. Wang, B. Schiele, X. Xie, B. Raj, and M. Savvides, “Softmatch: Addressing the quantity-quality trade-off in semi-supervised learning,” arXiv preprint arXiv:2301.10921, 2023.
  32. G. Li, X. Li, Y. Wang, Y. Wu, D. Liang, and S. Zhang, “Pseco: Pseudo labeling and consistency training for semi-supervised object detection,” in Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part IX.   Springer, 2022, pp. 457–472.
  33. ——, “Dtg-ssod: Dense teacher guidance for semi-supervised object detection,” arXiv preprint arXiv:2207.05536, 2022.
  34. M. Xu, Z. Zhang, H. Hu, J. Wang, L. Wang, F. Wei, X. Bai, and Z. Liu, “End-to-end semi-supervised object detection with soft teacher,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021, pp. 3060–3069.
  35. S. S. Rambhatla, S. Suri, R. Chellappa, and A. Shrivastava, “Sparsely annotated object detection: A region-based semi-supervised approach,” arXiv preprint arXiv:2201.04620, 2022.
  36. H. Wang, L. Liu, B. Zhang, J. Zhang, W. Zhang, Z. Gan, Y. Wang, C. Wang, and H. Wang, “Calibrated teacher for sparsely annotated object detection,” arXiv preprint arXiv:2303.07582, 2023.
  37. J. Yoon, S. Hong, and M.-K. Choi, “Semi-supervised object detection with sparsely annotated dataset,” in 2021 IEEE International Conference on Image Processing (ICIP).   IEEE, 2021, pp. 719–723.
  38. T. Wang, T. Yang, J. Cao, and X. Zhang, “Co-mining: Self-supervised learning for sparsely annotated object detection,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 4, 2021, pp. 2800–2808.
  39. E. Arazo, D. Ortego, P. Albert, N. E. O’Connor, and K. McGuinness, “Pseudo-labeling and confirmation bias in deep semi-supervised learning,” in 2020 International Joint Conference on Neural Networks (IJCNN).   IEEE, 2020, pp. 1–8.
  40. E. D. Cubuk, B. Zoph, J. Shlens, and Q. V. Le, “Randaugment: Practical data augmentation with no separate search,” CoRR, vol. abs/1909.13719, 2019. [Online]. Available: http://arxiv.org/abs/1909.13719
  41. K. Sohn, Z. Zhang, C. Li, H. Zhang, C. Lee, and T. Pfister, “A simple semi-supervised learning framework for object detection,” CoRR, vol. abs/2005.04757, 2020.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now