Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 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

SculptDiff: Learning Robotic Clay Sculpting from Humans with Goal Conditioned Diffusion Policy (2403.10401v1)

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

Abstract: Manipulating deformable objects remains a challenge within robotics due to the difficulties of state estimation, long-horizon planning, and predicting how the object will deform given an interaction. These challenges are the most pronounced with 3D deformable objects. We propose SculptDiff, a goal-conditioned diffusion-based imitation learning framework that works with point cloud state observations to directly learn clay sculpting policies for a variety of target shapes. To the best of our knowledge this is the first real-world method that successfully learns manipulation policies for 3D deformable objects. For sculpting videos and access to our dataset and hardware CAD models, see the project website: https://sites.google.com/andrew.cmu.edu/imitation-sculpting/home

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. K. Kimble, J. Albrecht, M. Zimmerman, and J. Falco, “Performance measures to benchmark the grasping, manipulation, and assembly of deformable objects typical to manufacturing applications,” Frontiers in Robotics and AI, vol. 9, p. 999348, 2022.
  2. N. Lv, J. Liu, and Y. Jia, “Dynamic modeling and control of deformable linear objects for single-arm and dual-arm robot manipulations,” Transactions on Robotics, vol. 38, no. 4, pp. 2341–2353, 2022.
  3. F. Liu, Z. Li, Y. Han, J. Lu, F. Richter, and M. C. Yip, “Real-to-sim registration of deformable soft tissue with position-based dynamics for surgical robot autonomy,” in International Conference on Robotics and Automation.   IEEE, 2021, pp. 12 328–12 334.
  4. A. Bartsch, C. Avra, and A. B. Farimani, “SculptBot: Pre-Trained Models for 3D Deformable Object Manipulation,” arXiv preprint arXiv:2309.08728, 2023.
  5. H. Shi, H. Xu, Z. Huang, Y. Li, and J. Wu, “RoboCraft: Learning to see, simulate, and shape elasto-plastic objects in 3D with graph networks,” The International Journal of Robotics Research, p. 02783649231219020, 2023.
  6. H. Shi, H. Xu, S. Clarke, Y. Li, and J. Wu, “RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools,” arXiv preprint arXiv:2306.14447, 2023.
  7. 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 International Conference on Intelligent Robots and Systems.   IEEE, 2023, pp. 4920–4925.
  8. C. Qi, X. Lin, and D. Held, “Learning closed-loop dough manipulation using a differentiable reset module,” Robotics and Automation Letters, vol. 7, no. 4, pp. 9857–9864, 2022.
  9. D. A. Pomerleau, “ALVINN: An autonomous land vehicle in a neural network,” Advances in neural information processing systems, vol. 1, 1988.
  10. J. Pari, N. M. Shafiullah, S. P. Arunachalam, and L. Pinto, “The surprising effectiveness of representation learning for visual imitation,” arXiv preprint arXiv:2112.01511, 2021.
  11. A. Brohan, N. Brown, J. Carbajal, Y. Chebotar, J. Dabis, C. Finn, K. Gopalakrishnan, K. Hausman, A. Herzog, J. Hsu et al., “Rt-1: Robotics transformer for real-world control at scale,” arXiv preprint arXiv:2212.06817, 2022.
  12. E. Jang, A. Irpan, M. Khansari, D. Kappler, F. Ebert, C. Lynch, S. Levine, and C. Finn, “Bc-z: Zero-shot task generalization with robotic imitation learning,” in Conference on Robot Learning.   PMLR, 2022, pp. 991–1002.
  13. N. M. Shafiullah, Z. Cui, A. A. Altanzaya, and L. Pinto, “Behavior Transformers: Cloning k𝑘kitalic_k modes with one stone,” Advances in neural information processing systems, vol. 35, pp. 22 955–22 968, 2022.
  14. T. Z. Zhao, V. Kumar, S. Levine, and C. Finn, “Learning fine-grained bimanual manipulation with low-cost hardware,” arXiv preprint arXiv:2304.13705, 2023.
  15. A. George and A. B. Farimani, “One ACT Play: Single Demonstration Behavior Cloning with Action Chunking Transformers,” arXiv preprint arXiv:2309.10175, 2023.
  16. H. Bharadhwaj, J. Vakil, M. Sharma, A. Gupta, S. Tulsiani, and V. Kumar, “Roboagent: Generalization and efficiency in robot manipulation via semantic augmentations and action chunking,” arXiv preprint arXiv:2309.01918, 2023.
  17. C. Chi, S. Feng, Y. Du, Z. Xu, E. Cousineau, B. Burchfiel, and S. Song, “Diffusion policy: Visuomotor policy learning via action diffusion,” arXiv preprint arXiv:2303.04137, 2023.
  18. X. Yu, L. Tang, Y. Rao, T. Huang, J. Zhou, and J. Lu, “Point-bert: Pre-training 3d point cloud transformers with masked point modeling,” in Conference on Computer Vision and Pattern Recognition, 2022, pp. 19 313–19 322.
  19. S. Huo, A. Duan, C. Li, P. Zhou, W. Ma, H. Wang, and D. Navarro-Alarcon, “Keypoint-based planar bimanual shaping of deformable linear objects under environmental constraints with hierarchical action framework,” Robotics and Automation Letters, vol. 7, no. 2, pp. 5222–5229, 2022.
  20. J. Xiang, H. Dinkel, H. Zhao, N. Gao, B. Coltin, T. Smith, and T. Bretl, “TrackDLO: Tracking Deformable Linear Objects Under Occlusion with Motion Coherence,” Robotics and Automation Letters, 2023.
  21. A. Caporali, K. Galassi, R. Zanella, and G. Palli, “FASTDLO: Fast deformable linear objects instance segmentation,” Robotics and Automation Letters, vol. 7, no. 4, pp. 9075–9082, 2022.
  22. J. Zhu, B. Navarro, R. Passama, P. Fraisse, A. Crosnier, and A. Cherubini, “Robotic manipulation planning for shaping deformable linear objects withenvironmental contacts,” Robotics and Automation Letters, vol. 5, no. 1, pp. 16–23, 2019.
  23. M. Yu, K. Lv, C. Wang, M. Tomizuka, and X. Li, “A coarse-to-fine framework for dual-arm manipulation of deformable linear objects with whole-body obstacle avoidance,” in International Conference on Robotics and Automation.   IEEE, 2023, pp. 10 153–10 159.
  24. W. Zhang, K. Schmeckpeper, P. Chaudhari, and K. Daniilidis, “Deformable linear object prediction using locally linear latent dynamics,” in International Conference on Robotics and Automation.   IEEE, 2021, pp. 13 503–13 509.
  25. W. Yan, A. Vangipuram, P. Abbeel, and L. Pinto, “Learning predictive representations for deformable objects using contrastive estimation,” in Conference on Robot Learning.   PMLR, 2021, pp. 564–574.
  26. Z. Huang, X. Lin, and D. Held, “Mesh-based dynamics with occlusion reasoning for cloth manipulation,” arXiv preprint arXiv:2206.02881, 2022.
  27. T. Weng, S. M. Bajracharya, Y. Wang, K. Agrawal, and D. Held, “Fabricflownet: Bimanual cloth manipulation with a flow-based policy,” in Conference on Robot Learning.   PMLR, 2022, pp. 192–202.
  28. X. Lin, Y. Wang, Z. Huang, and D. Held, “Learning visible connectivity dynamics for cloth smoothing,” in Conference on Robot Learning.   PMLR, 2022, pp. 256–266.
  29. 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,” arXiv preprint arXiv:2104.03311, 2021.
  30. S. Chen, Y. Liu, S. W. Yao, J. Li, T. Fan, and J. Pan, “Diffsrl: Learning dynamical state representation for deformable object manipulation with differentiable simulation,” Robotics and Automation Letters, vol. 7, no. 4, pp. 9533–9540, 2022.
  31. 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,” International Conference on Learning Representations, 2022.
  32. S. Li, Z. Huang, T. Chen, T. Du, H. Su, J. B. Tenenbaum, and C. Gan, “DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics,” International Conference on Learning Representations, 2023.
  33. B. Thach, B. Y. Cho, A. Kuntz, and T. Hermans, “Learning visual shape control of novel 3D deformable objects from partial-view point clouds,” in International Conference on Robotics and Automation.   IEEE, 2022, pp. 8274–8281.
  34. B. Shen, Z. Jiang, C. Choy, S. Savarese, L. J. Guibas, A. Anandkumar, and Y. Zhu, “Action-conditional implicit visual dynamics for deformable object manipulation,” The International Journal of Robotics Research, p. 02783649231191222, 2023.
  35. X. Lin, C. Qi, Y. Zhang, Z. Huang, K. Fragkiadaki, Y. Li, C. Gan, and D. Held, “Planning with spatial-temporal abstraction from point clouds for deformable object manipulation,” in Conference on Robot Learning, 2022.
  36. N. Xuejuan, L. Jingtai, S. Lei, L. Zheng, and C. Xinwei, “Robot 3D sculpturing based on extracted NURBS,” in International Conference on Robotics and Biomimetics.   IEEE, 2007, pp. 1936–1941.
  37. Z. Ma, S. Duenser, C. Schumacher, R. Rust, M. Bächer, F. Gramazio, M. Kohler, and S. Coros, “Robotsculptor: Artist-directed robotic sculpting of clay,” in ACM Symposium on Computational Fabrication, 2020, pp. 1–12.
  38. M. Zhang, Z. Cheng, S. T. R. Shiu, J. Liang, C. Fang, Z. Ma, and S. J. Wang, “CoSculpt: An AI-Embedded Human-Robot Collaboration System for Sculptural Creation,” in Human Systems Engineering and Design: Future Trends and Applications.   AHFE International, 2023.
  39. S. Li, Z. Huang, T. Du, H. Su, J. B. Tenenbaum, and C. Gan, “Contact points discovery for soft-body manipulations with differentiable physics,” International Conference on Learning Representations, 2022.
  40. H. Zhu, Y. Wang, D. Huang, W. Ye, W. Ouyang, and T. He, “Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning,” arXiv preprint arXiv:2402.02500, 2024.
  41. D. Yarats, I. Kostrikov, and R. Fergus, “Image augmentation is all you need: Regularizing deep reinforcement learning from pixels,” in International conference on learning representations, 2020.
  42. J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” Advances in neural information processing systems, vol. 33, pp. 6840–6851, 2020.
  43. X. Li, Y. Liu, L. Lian, H. Yang, Z. Dong, D. Kang, S. Zhang, and K. Keutzer, “Q-Diffusion: Quantizing Diffusion Models,” in International Conference on Computer Vision, October 2023, pp. 17 535–17 545.
  44. A. X. Chang, T. Funkhouser, L. Guibas, P. Hanrahan, Q. Huang, Z. Li, S. Savarese, M. Savva, S. Song, H. Su et al., “Shapenet: An information-rich 3d model repository,” arXiv preprint arXiv:1512.03012, 2015.
Citations (3)
View on Semantic Scholar

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