Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
153 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

A Contact Model based on Denoising Diffusion to Learn Variable Impedance Control for Contact-rich Manipulation (2403.13221v1)

Published 20 Mar 2024 in cs.RO

Abstract: In this paper, a novel approach is proposed for learning robot control in contact-rich tasks such as wiping, by developing Diffusion Contact Model (DCM). Previous methods of learning such tasks relied on impedance control with time-varying stiffness tuning by performing Bayesian optimization by trial-and-error with robots. The proposed approach aims to reduce the cost of robot operation by predicting the robot contact trajectories from the variable stiffness inputs and using neural models. However, contact dynamics are inherently highly nonlinear, and their simulation requires iterative computations such as convex optimization. Moreover, approximating such computations by using finite-layer neural models is difficult. To overcome these limitations, the proposed DCM used the denoising diffusion models that could simulate the complex dynamics via iterative computations of multi-step denoising, thus improving the prediction accuracy. Stiffness tuning experiments conducted in simulated and real environments showed that the DCM achieved comparable performance to a conventional robot-based optimization method while reducing the number of robot trials.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. M. J. Pollayil, F. Angelini, G. Xin, M. Mistry, S. Vijayakumar, A. Bicchi, and M. Garabini, “Choosing stiffness and damping for optimal impedance planning,” IEEE Transactions on Robotics, 2022.
  2. M. Okada, M. Komatsu, R. Okumura, and T. Taniguchi, “Learning compliant stiffness by impedance control-aware task segmentation and multi-objective bayesian optimization with priors,” in IROS, 2023.
  3. L. Johannsmeier, M. Gerchow, and S. Haddadin, “A framework for robot manipulation: Skill formalism, meta learning and adaptive control,” in ICRA, 2019.
  4. Z. Wu, W. Lian, C. Wang, M. Li, S. Schaal, and M. Tomizuka, “Prim-LAfD: A framework to learn and adapt primitive-based skills from demonstrations for insertion tasks,” arXiv:2212.00955, 2022.
  5. Y. Hu, X. Wu, P. Geng, and Z. Li, “Evolution strategies learning with variable impedance control for grasping under uncertainty,” IEEE Transactions on Industrial Electronics, 2019.
  6. M. Salehi, G. Vossoughi, M. Vajedi, and M. Brooshaki, “Impedance control and gain tuning of flexible base moving manipulators using pso method,” in ICRA, IEEE, 2008.
  7. M. M. Fateh and M. M. Zirkohi, “Adaptive impedance control of a hydraulic suspension system using particle swarm optimisation,” Vehicle System Dynamics, vol. 49, no. 12, pp. 1951–1965, 2011.
  8. V. Azimi, D. Simon, and H. Richter, “Stable robust adaptive impedance control of a prosthetic leg,” in Dynamic Systems and Control Conference, American Society of Mechanical Engineers, 2015.
  9. E. Todorov, T. Erez, and Y. Tassa, “Mujoco: A physics engine for model-based control,” in IROS, pp. 5026–5033, 2012.
  10. E. Coumans and Y. Bai, “PyBullet, a python module for physics simulation for games, robotics and machine learning,” 2016.
  11. Q. L. Lidec, W. Jallet, L. Montaut, I. Laptev, C. Schmid, and J. Carpentier, “Contact models in robotics: a comparative analysis,” arXiv:2304.06372, 2023.
  12. M. Macklin, K. Storey, M. Lu, P. Terdiman, N. Chentanez, S. Jeschke, and M. Müller, “Small steps in physics simulation,” 2019.
  13. J. Hwangbo, J. Lee, and M. Hutter, “Per-contact iteration method for solving contact dynamics,” IEEE Robotics and Automation Letters, vol. 3, no. 2, pp. 895–902, 2018.
  14. J. Lee, M. X. Grey, S. Ha, T. Kunz, et al., “DART: Dynamic animation and robotics toolkit,” The Journal of Open Source Software, vol. 3, no. 22, p. 500, 2018.
  15. R. Tedrake et al., “Drake: Model-based design and verification for robotics,” 2019.
  16. R. Smith et al., “Open dynamics engine, 2008,” URL: http://www.ode.org, vol. 5, 2005.
  17. V. Acary, M. Brémond, and O. Huber, “On solving contact problems with coulomb friction: formulations and numerical comparisons,” Advanced Topics in Nonsmooth Dynamics: Transactions of the European Network for Nonsmooth Dynamics, pp. 375–457, 2018.
  18. J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” NeurIPS, vol. 33, pp. 6840–6851, 2020.
  19. Y. Song, J. Sohl-Dickstein, D. P. Kingma, A. Kumar, S. Ermon, and B. Poole, “Score-based generative modeling through stochastic differential equations,” in ICLR, 2021.
  20. A. Nagabandi, G. Kahn, R. S. Fearing, and S. Levine, “Neural network dynamics for model-based deep reinforcement learning with model-free fine-tuning,” in ICRA, 2018.
  21. K. Chua, R. Calandra, R. McAllister, and S. Levine, “Deep reinforcement learning in a handful of trials using probabilistic dynamics models,” NeurIPS, 2018.
  22. A. Nagabandi, K. Konolige, S. Levine, and V. Kumar, “Deep dynamics models for learning dexterous manipulation,” in CoRL, PMLR, 2020.
  23. M. Okada and T. Taniguchi, “Variational inference MPC for bayesian model-based reinforcement learning,” in CoRL, PMLR, 2020.
  24. D. Hafner, T. Lillicrap, J. Ba, and M. Norouzi, “Dream to control: Learning behaviors by latent imagination,” ICLR, 2020.
  25. D. Hafner, T. Lillicrap, M. Norouzi, and J. Ba, “Mastering atari with discrete world models,” in ICLR, 2021.
  26. M. Okada, N. Kosaka, and T. Taniguchi, “PlaNet of the bayesians: Reconsidering and improving deep planning network by incorporating bayesian inference,” in IROS, 2020.
  27. P. Wu, A. Escontrela, D. Hafner, P. Abbeel, and K. Goldberg, “Daydreamer: World models for physical robot learning,” in CoRL, 2023.
  28. J. Gao, Y. Zhou, and T. Asfour, “Learning compliance adaptation in contact-rich manipulation,” arXiv:2005.00227, 2020.
  29. A. S. Anand, J. T. Gravdahl, and F. J. Abu-Dakka, “Model-based variable impedance learning control for robotic manipulation,” Robotics and Autonomous Systems, vol. 170, p. 104531, 2023.
  30. M. Janner, Y. Du, J. B. Tenenbaum, and S. Levine, “Planning with diffusion for flexible behavior synthesis,” in ICML, 2022.
  31. A. Ajay, Y. Du, A. Gupta, J. Tenenbaum, T. Jaakkola, and P. Agrawal, “Is conditional generative modeling all you need for decision-making?,” ICLR, 2022.
  32. J. Carvalho, A. T. Le, M. Baierl, D. Koert, and J. Peters, “Motion planning diffusion: Learning and planning of robot motions with diffusion models,” in IROS, IEEE, 2023.
  33. U. A. Mishra and Y. Chen, “Reorientdiff: Diffusion model based reorientation for object manipulation,” arXiv:2303.12700, 2023.
  34. Z. Wang, J. J. Hunt, and M. Zhou, “Diffusion policies as an expressive policy class for offline reinforcement learning,” in ICLR, 2023.
  35. P. Hansen-Estruch, I. Kostrikov, M. Janner, J. G. Kuba, and S. Levine, “iDQL: Implicit q-learning as an actor-critic method with diffusion policies,” arXiv:2304.10573, 2023.
  36. C. Chi, S. Feng, Y. Du, Z. Xu, E. Cousineau, B. Burchfiel, and S. Song, “Diffusion policy: Visuomotor policy learning via action diffusion,” arXiv:2303.04137, 2023.
  37. F. Ficuciello, L. Villani, and B. Siciliano, “Variable impedance control of redundant manipulators for intuitive human–robot physical interaction,” IEEE Transactions on Robotics, vol. 31, no. 4, pp. 850–863, 2015.
  38. K. Kronander and A. Billard, “Stability considerations for variable impedance control,” IEEE Transactions on Robotics, vol. 32, no. 5, pp. 1298–1305, 2016.
  39. Y. Sun, L. Dong, S. Huang, S. Ma, Y. Xia, J. Xue, J. Wang, and F. Wei, “Retentive network: A successor to transformer for large language models,” arXiv:2307.08621, 2023.
  40. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” NeurIPS, 2017.
  41. J. Baxter, “A model of inductive bias learning,” Journal of artificial intelligence research, vol. 12, pp. 149–198, 2000.
  42. Y. Ozaki, Y. Tanigaki, S. Watanabe, and M. Onishi, “Multiobjective tree-structured parzen estimator for computationally expensive optimization problems,” in GECCO, 2020.
  43. Y. Zhu, J. Wong, A. Mandlekar, R. Martín-Martín, A. Joshi, S. Nasiriany, and Y. Zhu, “robosuite: A modular simulation framework and benchmark for robot learning,” in arXiv:2009.12293, 2020.
  44. A. Brohan, N. Brown, J. Carbajal, et al., “RT-1: Robotics transformer for real-world control at scale,” arXiv:2212.06817, 2022.
  45. A. Brohan, N. Brown, J. Carbajal, Y. Chebotar, et al., “RT-2: Vision-language-action models transfer web knowledge to robotic control,” arXiv:2307.15818, 2023.
  46. A. Q. Nichol and P. Dhariwal, “Improved denoising diffusion probabilistic models,” in ICML, 2021.

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