Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

Learning Goal-oriented Bimanual Dough Rolling Using Dynamic Heterogeneous Graph Based on Human Demonstration (2410.22355v1)

Published 15 Oct 2024 in cs.RO and cs.AI

Abstract: Soft object manipulation poses significant challenges for robots, requiring effective techniques for state representation and manipulation policy learning. State representation involves capturing the dynamic changes in the environment, while manipulation policy learning focuses on establishing the relationship between robot actions and state transformations to achieve specific goals. To address these challenges, this research paper introduces a novel approach: a dynamic heterogeneous graph-based model for learning goal-oriented soft object manipulation policies. The proposed model utilizes graphs as a unified representation for both states and policy learning. By leveraging the dynamic graph, we can extract crucial information regarding object dynamics and manipulation policies. Furthermore, the model facilitates the integration of demonstrations, enabling guided policy learning. To evaluate the efficacy of our approach, we designed a dough rolling task and conducted experiments using both a differentiable simulator and a real-world humanoid robot. Additionally, several ablation studies were performed to analyze the effect of our method, demonstrating its superiority in achieving human-like behavior.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (23)
  1. H. Yin, A. Varava, and D. Kragic, “Modeling, learning, perception, and control methods for deformable object manipulation,” Science Robotics, vol. 6, no. 54, p. eabd8803, 2021.
  2. Z. Sun, Z. Wang, J. Liu, M. Li, and F. Chen, “Mixline: A hybrid reinforcement learning framework for long-horizon bimanual coffee stirring task,” in International Conference on Intelligent Robotics and Applications, pp. 627–636, Springer, 2022.
  3. J. Liu, Y. Chen, Z. Dong, S. Wang, S. Calinon, M. Li, and F. Chen, “Robot cooking with stir-fry: Bimanual non-prehensile manipulation of semi-fluid objects,” IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 5159–5166, 2022.
  4. Y. Hu, L. Anderson, T. Li, Q. Sun, N. Carr, J. Ragan-Kelley, and F. Durand, “Difftaichi: Differentiable programming for physical simulation,” in 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020, OpenReview.net, 2020.
  5. H. Shi, H. Xu, Z. Huang, Y. Li, and J. Wu, “Robocraft: Learning to see, simulate, and shape elasto-plastic objects with graph networks,” 2022.
  6. S. Schaal, “Dynamic movement primitives-a framework for motor control in humans and humanoid robotics,” in Adaptive motion of animals and machines, pp. 261–280, Springer, 2006.
  7. S. Calinon, “A tutorial on task-parameterized movement learning and retrieval,” Intelligent service robotics, vol. 9, no. 1, pp. 1–29, 2016.
  8. J. Ho and S. Ermon, “Generative adversarial imitation learning,” Advances in neural information processing systems, vol. 29, 2016.
  9. M. Savva, J. Malik, D. Parikh, D. Batra, A. Kadian, O. Maksymets, Y. Zhao, E. Wijmans, B. Jain, J. Straub, J. Liu, and V. Koltun, “Habitat: A platform for embodied AI research,” in 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 9338–9346, IEEE, 2019.
  10. E. Todorov, T. Erez, and Y. Tassa, “Mujoco: A physics engine for model-based control,” in 2012 IEEE/RSJ international conference on intelligent robots and systems, pp. 5026–5033, IEEE, 2012.
  11. Z. Huang, Y. Hu, T. Du, S. Zhou, H. Su, J. B. Tenenbaum, and C. Gan, “Plasticinelab: A soft-body manipulation benchmark with differentiable physics,” in International Conference on Learning Representations (ICLR), 2020.
  12. J. Liu, J. Shou, Z. Fu, H. Zhou, R. Xie, J. Zhang, J. Fei, and Y. Zhao, “Efficient reinforcement learning control for continuum robots based on inexplicit prior knowledge,” arXiv preprint arXiv:2002.11573, 2020.
  13. N. Figueroa, A. L. P. Ureche, and A. Billard, “Learning complex sequential tasks from demonstration: A pizza dough rolling case study,” in 2016 11th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pp. 611–612, Ieee, 2016.
  14. S. Calinon, T. Alizadeh, and D. G. Caldwell, “On improving the extrapolation capability of task-parameterized movement models,” in 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 610–616, IEEE, 2013.
  15. X. Lin, Z. Huang, Y. Li, J. B. Tenenbaum, D. Held, and C. Gan, “Diffskill: Skill abstraction from differentiable physics for deformable object manipulations with tools,” arXiv preprint arXiv:2203.17275, 2022.
  16. A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever, et al., “Language models are unsupervised multitask learners,” OpenAI blog, vol. 1, no. 8, p. 9, 2019.
  17. J. Liu, Z. Li, W. Lin, S. Calinon, K. C. Tan, and F. Chen, “Softgpt: Learn goal-oriented soft object manipulation skills by generative pre-trained heterogeneous graph transformer,” in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4920–4925, IEEE, 2023.
  18. Z. Weng, F. Paus, A. Varava, H. Yin, T. Asfour, and D. Kragic, “Graph-based task-specific prediction models for interactions between deformable and rigid objects,” in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5741–5748, IEEE, 2021.
  19. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907, 2016.
  20. A. Kumar, A. Zhou, G. Tucker, and S. Levine, “Conservative q-learning for offline reinforcement learning,” in Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual (H. Larochelle, M. Ranzato, R. Hadsell, M. Balcan, and H. Lin, eds.), 2020.
  21. J. Liu, H. Sim, C. Li, K. C. Tan, and F. Chen, “Birp: Learning robot generalized bimanual coordination using relative parameterization method on human demonstration,” in 2023 62nd IEEE Conference on Decision and Control (CDC), pp. 8300–8305, IEEE, 2023.
  22. S. Calinon and D. Lee, “Learning control,” in Humanoid robotics: A reference, pp. 1–52, Springer Netherlands, 2017.
  23. J. Liu, Z. Dong, C. Li, Z. Li, M. Yu, D. Delehelle, and F. Chen, “Rofunc: The full process python package for robot learning from demonstration and robot manipulation,” 2023.

Summary

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

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

Tweets