Papers
Topics
Authors
Recent
2000 character limit reached

CoverLib: Classifiers-equipped Experience Library by Iterative Problem Distribution Coverage Maximization for Domain-tuned Motion Planning (2405.02968v4)

Published 5 May 2024 in cs.RO, cs.AI, and cs.LG

Abstract: Library-based methods are known to be very effective for fast motion planning by adapting an experience retrieved from a precomputed library. This article presents CoverLib, a principled approach for constructing and utilizing such a library. CoverLib iteratively adds an experience-classifier-pair to the library, where each classifier corresponds to an adaptable region of the experience within the problem space. This iterative process is an active procedure, as it selects the next experience based on its ability to effectively cover the uncovered region. During the query phase, these classifiers are utilized to select an experience that is expected to be adaptable for a given problem. Experimental results demonstrate that CoverLib effectively mitigates the trade-off between plannability and speed observed in global (e.g. sampling-based) and local (e.g. optimization-based) methods. As a result, it achieves both fast planning and high success rates over the problem domain. Moreover, due to its adaptation-algorithm-agnostic nature, CoverLib seamlessly integrates with various adaptation methods, including nonlinear programming-based and sampling-based algorithms.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. L. E. Kavraki, P. Svestka, J.-C. Latombe, and M. H. Overmars, “Probabilistic roadmaps for path planning in high-dimensional configuration spaces,” IEEE trans. on Robot. and Autom., vol. 12, no. 4, pp. 566–580, 1996.
  2. S. M. LaValle and J. J. Kuffner Jr, “Randomized kinodynamic planning,” Int. J. Robot. Res., vol. 20, no. 5, pp. 378–400, 2001.
  3. M. Zucker, N. Ratliff, A. D. Dragan, M. Pivtoraiko, M. Klingensmith, C. M. Dellin, J. A. Bagnell, and S. S. Srinivasa, “Chomp: Covariant hamiltonian optimization for motion planning,” Int. J. Robot. Res., vol. 32, no. 9-10, pp. 1164–1193, 2013.
  4. J. Schulman, Y. Duan, J. Ho, A. Lee, I. Awwal, H. Bradlow, J. Pan, S. Patil, K. Goldberg, and P. Abbeel, “Motion planning with sequential convex optimization and convex collision checking,” Int. J. Robot. Res., vol. 33, no. 9, pp. 1251–1270, 2014.
  5. N. Jetchev and M. Toussaint, “Fast motion planning from experience: trajectory prediction for speeding up movement generation,” Auton. Robots, vol. 34, no. 1, pp. 111–127, 2013.
  6. K. Hauser, “Learning the problem-optimum map: Analysis and application to global optimization in robotics,” IEEE Trans. Robot., vol. 33, no. 1, pp. 141–152, 2016.
  7. T. S. Lembono, A. Paolillo, E. Pignat, and S. Calinon, “Memory of motion for warm-starting trajectory optimization,” IEEE Robot. Autom. Lett., vol. 5, no. 2, pp. 2594–2601, 2020.
  8. E. Dantec, R. Budhiraja, A. Roig, T. Lembono, G. Saurel, O. Stasse, P. Fernbach, S. Tonneau, S. Vijayakumar, S. Calinon et al., “Whole body model predictive control with a memory of motion: Experiments on a torque-controlled talos,” in Proc. IEEE Int. Conf. Robot. Autom., 2021, pp. 8202–8208.
  9. D. Berenson, P. Abbeel, and K. Goldberg, “A robot path planning framework that learns from experience,” in Proc. IEEE Int. Conf. Robot. Autom., 2012, pp. 3671–3678.
  10. È. Pairet, C. Chamzas, Y. Petillot, and L. E. Kavraki, “Path planning for manipulation using experience-driven random trees,” IEEE Robot. Autom. Lett., vol. 6, no. 2, pp. 3295–3302, 2021.
  11. F. Islam, O. Salzman, and M. Likhachev, “Provable indefinite-horizon real-time planning for repetitive tasks,” in Proc. Int. Conf. Autom. Plan. Sched., vol. 29, 2019, pp. 716–724.
  12. F. Islam, O. Salzman, A. Agarwal, and M. Likhachev, “Provably constant-time planning and replanning for real-time grasping objects off a conveyor belt,” Int. J. Robot. Res., vol. 40, no. 12-14, pp. 1370–1384, 2021.
  13. F. Islam, C. Paxton, C. Eppner, B. Peele, M. Likhachev, and D. Fox, “Alternative paths planner (app) for provably fixed-time manipulation planning in semi-structured environments,” in Proc. IEEE Int. Conf. Robot. Autom., 2021, pp. 6534–6540.
  14. P. Lehner and A. Albu-Schäffer, “Repetition sampling for efficiently planning similar constrained manipulation tasks,” in Proc. IEEE/RSJ Int. Conf. Intell. Robots. Syst.   IEEE, 2017, pp. 2851–2856.
  15. B. Ichter, J. Harrison, and M. Pavone, “Learning sampling distributions for robot motion planning,” in Proc. IEEE Int. Conf. Robot. Autom., 2018, pp. 7087–7094.
  16. C. Chamzas, A. Shrivastava, and L. E. Kavraki, “Using local experiences for global motion planning,” in Proc. IEEE Int. Conf. Robot. Autom., 2019, pp. 8606–8612.
  17. C. Chamzas, A. Cullen, A. Shrivastava, and L. E. Kavraki, “Learning to retrieve relevant experiences for motion planning,” in Proc. IEEE Int. Conf. Robot. Autom., 2022, pp. 7233–7240.
  18. M. Zucker, J. Kuffner, and J. A. Bagnell, “Adaptive workspace biasing for sampling-based planners,” in Proc. IEEE Int. Conf. Robot. Autom.   IEEE, 2008, pp. 3757–3762.
  19. R. Terasawa, Y. Ariki, T. Narihira, T. Tsuboi, and K. Nagasaka, “3d-cnn based heuristic guided task-space planner for faster motion planning,” in Proc. IEEE Int. Conf. Robot. Autom., 2020, pp. 9548–9554.
  20. B. Ichter, E. Schmerling, T.-W. E. Lee, and A. Faust, “Learned critical probabilistic roadmaps for robotic motion planning,” in Proc. IEEE Int. Conf. Robot. Autom., 2020, pp. 9535–9541.
  21. A. H. Qureshi, Y. Miao, A. Simeonov, and M. C. Yip, “Motion planning networks: Bridging the gap between learning-based and classical motion planners,” IEEE Trans. Robot., vol. 37, no. 1, pp. 48–66, 2020.
  22. T. Ando, H. Iino, H. Mori, R. Torishima, K. Takahashi, S. Yamaguchi, D. Okanohara, and T. Ogata, “Learning-based collision-free planning on arbitrary optimization criteria in the latent space through cgans,” Adv. Robot., vol. 37, no. 10, pp. 621–633, 2023.
  23. B. Ichter and M. Pavone, “Robot motion planning in learned latent spaces,” IEEE Robot. Autom. Lett., vol. 4, no. 3, pp. 2407–2414, 2019.
  24. D. Coleman, I. A. Şucan, M. Moll, K. Okada, and N. Correll, “Experience-based planning with sparse roadmap spanners,” in Proc. IEEE Int. Conf. Robot. Autom., 2015, pp. 900–905.
  25. C. R. Garrett, R. Chitnis, R. Holladay, B. Kim, T. Silver, L. P. Kaelbling, and T. Lozano-Pérez, “Integrated task and motion planning,” Annu. Rev. Control, Robot., Auton. Syst., vol. 4, pp. 265–293, 2021.
  26. G. L. Nemhauser, L. A. Wolsey, and M. L. Fisher, “An analysis of approximations for maximizing submodular set functions―i,” Math. program., vol. 14, pp. 265–294, 1978.
  27. A. Krause and D. Golovin, “Submodular function maximization.” Tractability, vol. 3, no. 71-104, p. 3, 2014.
  28. N. Hansen, S. D. Müller, and P. Koumoutsakos, “Reducing the time complexity of the derandomized evolution strategy with covariance matrix adaptation (cma-es),” Evol. Comput., vol. 11, no. 1, pp. 1–18, 2003.
  29. M. Nomura and M. Shibata, “cmaes: A simple yet practical python library for cma-es,” arXiv preprint arXiv:2402.01373, 2024.
  30. B. Stellato, G. Banjac, P. Goulart, A. Bemporad, and S. Boyd, “Osqp: An operator splitting solver for quadratic programs,” Math. Program. Comput., vol. 12, no. 4, pp. 637–672, 2020.
  31. P. Virtanen, R. Gommers, T. E. Oliphant, M. Haberland, T. Reddy, D. Cournapeau, E. Burovski, P. Peterson, W. Weckesser, J. Bright et al., “Scipy 1.0: fundamental algorithms for scientific computing in python,” Nature methods, vol. 17, no. 3, pp. 261–272, 2020.
  32. R. Tedrake, “Underactuated robotics: Learning, planning, and control for efficient and agile machines course notes for mit 6.832,” Working draft edition, vol. 3, no. 4, p. 2, 2009.
  33. L. Janson, E. Schmerling, A. Clark, and M. Pavone, “Fast marching tree: A fast marching sampling-based method for optimal motion planning in many dimensions,” Int. J. Robot. Res., vol. 34, no. 7, pp. 883–921, 2015.
  34. D. J. Webb and J. Van Den Berg, “Kinodynamic rrt*: Asymptotically optimal motion planning for robots with linear dynamics,” in Proc. IEEE Int. Conf. Robot. Autom., 2013, pp. 5054–5061.
  35. K. Kojima, T. Karasawa, T. Kozuki, E. Kuroiwa, S. Yukizaki, S. Iwaishi, T. Ishikawa, R. Koyama, S. Noda, F. Sugai et al., “Development of life-sized high-power humanoid robot jaxon for real-world use,” in Proc. IEEE-RAS Int. Conf. Humanoid Robots., 2015, pp. 838–843.
  36. D. Kappler, F. Meier, J. Issac, J. Mainprice, C. G. Cifuentes, M. Wüthrich, V. Berenz, S. Schaal, N. Ratliff, and J. Bohg, “Real-time perception meets reactive motion generation,” IEEE Robot. Autom. Lett., vol. 3, no. 3, pp. 1864–1871, 2018.
  37. Z. Kingston, M. Moll, and L. E. Kavraki, “Sampling-based methods for motion planning with constraints,” Annu. Rev. Control, Robot., Auton. Syst., vol. 1, pp. 159–185, 2018.
  38. N. Hiraoka, H. Ishida, T. Hiraoka, K. Kojima, K. Okada, and M. Inaba, “Sampling-based global path planning using convex polytope approximation for narrow collision-free space of humanoid,” Int. J. of Humanoid Robot., 2024, in press and available online.
  39. I. A. Sucan, M. Moll, and L. E. Kavraki, “The open motion planning library,” IEEE Robot. Autom. Mag., vol. 19, no. 4, pp. 72–82, 2012.
  40. J. Pan, Z. Chen, and P. Abbeel, “Predicting initialization effectiveness for trajectory optimization,” in Proc. Int. Conf. Robot. Autom.   IEEE, 2014, pp. 5183–5190.
  41. C. Finn, P. Abbeel, and S. Levine, “Model-agnostic meta-learning for fast adaptation of deep networks,” in Proc. Int. Conf. Mach. Learn.   PMLR, 2017, pp. 1126–1135.
  42. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “Pytorch: An imperative style, high-performance deep learning library,” Proc. Adv. Neural Inf. Process. Syst., vol. 32, 2019.

Summary

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

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

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up