1932

Abstract

In recent years, the increasing complexity and safety-critical nature of robotic tasks have highlighted the importance of accurate and reliable robot models. This trend has led to a growing belief that, given enough data, traditional physics-based robot models can be replaced by appropriately trained deep networks or their variants. Simultaneously, there has been a renewed interest in physics-based simulation, fueled by the widespread use of simulators to train reinforcement learning algorithms in the sim-to-real paradigm. The primary objective of this review is to present a unified perspective on the process of determining robot models from data, commonly known as system identification or model learning in different subfields. The review aims to illuminate the key challenges encountered and highlight recent advancements in system identification for robotics. Specifically, we focus on recent breakthroughs that leverage the geometry of the identification problem and incorporate physics-based knowledge beyond mere first-principles model parameterizations. Through these efforts, we strive to provide a contemporary outlook on this problem, bridging classical findings with the latest progress in the field.

Loading

Article metrics loading...

/content/journals/10.1146/annurev-control-061523-102310
2024-07-10
2025-02-17
Loading full text...

Full text loading...

/deliver/fulltext/control/7/1/annurev-control-061523-102310.html?itemId=/content/journals/10.1146/annurev-control-061523-102310&mimeType=html&fmt=ahah

Literature Cited

  1. 1.
    Kristensen NR, Madsen H, Jørgensen SB. 2004.. Parameter estimation in stochastic grey-box models. . Automatica 40:(2):22537
    [Crossref] [Google Scholar]
  2. 2.
    Schoukens J, Ljung L. 2019.. Nonlinear system identification: a user-oriented road map. . IEEE Control Syst. Mag. 39:(6):2899
    [Crossref] [Google Scholar]
  3. 3.
    Wu P, Escontrela A, Hafner D, Abbeel P, Goldberg K. 2023.. DayDreamer: world models for physical robot learning. . In Proceedings of the 6th Conference on Robot Learning, ed. K Liu, D Kulic, J Ichnowski , pp. 222640 Proc. Mach. Learn. Res. 205. N.p. : PMLR
    [Google Scholar]
  4. 4.
    Brunot M, Janot A, Carrillo F, Cheong J, Noël JP. 2020.. Output error methods for robot identification. . J. Dyn. Syst. Meas. Control 142:(3): 031002
    [Crossref] [Google Scholar]
  5. 5.
    Swevers J, Ganseman C, Tukel DB, De Schutter J, Van Brussel H. 1997.. Optimal robot excitation and identification. . IEEE Trans. Robot. Autom. 13:(5):73040
    [Crossref] [Google Scholar]
  6. 6.
    Gautier M, Janot A, Vandanjon PO. 2012.. A new closed-loop output error method for parameter identification of robot dynamics. . IEEE Trans. Control Syst. Technol. 21:(2):42844
    [Crossref] [Google Scholar]
  7. 7.
    Choi K, Kwon J, Lee T, Park C, Pyo J, et al. 2020.. A hybrid dynamic model for the ambidex tendon-driven manipulator. . Mechatronics 69::102398
    [Crossref] [Google Scholar]
  8. 8.
    Hwangbo J, Lee J, Dosovitskiy A, Bellicoso D, Tsounis V, et al. 2019.. Learning agile and dynamic motor skills for legged robots. . Sci. Robot. 4:(26):eaau5872
    [Crossref] [Google Scholar]
  9. 9.
    Kwon J, Choi K, Park FC. 2021.. Kinodynamic model identification: a unified geometric approach. . IEEE Trans. Robot. 37:(4):110014
    [Crossref] [Google Scholar]
  10. 10.
    Pukelsheim F. 2006.. Optimal Design of Experiments. Philadelphia:: Soc. Ind. Appl. Math.
    [Google Scholar]
  11. 11.
    Pronzato L. 2008.. Optimal experimental design and some related control problems. . Automatica 44:(2):30325
    [Crossref] [Google Scholar]
  12. 12.
    Bonnet V, Fraisse P, Crosnier A, Gautier M, González A, Venture G. 2016.. Optimal exciting dance for identifying inertial parameters of an anthropomorphic structure. . IEEE Trans. Robot. 32:(4):82336
    [Crossref] [Google Scholar]
  13. 13.
    Brunke L, Greeff M, Hall AW, Yuan Z, Zhou S, et al. 2022.. Safe learning in robotics: from learning-based control to safe reinforcement learning. . Annu. Rev. Control Robot. Auton. Syst. 5::41144
    [Crossref] [Google Scholar]
  14. 14.
    Yasa O, Toshimitsu Y, Michelis MY, Jones LS, Filippi M, et al. 2023.. An overview of soft robotics. . Annu. Rev. Control Robot. Auton. Syst. 6::129
    [Crossref] [Google Scholar]
  15. 15.
    Atkeson CG, An CH, Hollerbach JM. 1986.. Estimation of inertial parameters of manipulator loads and links. . Int. J. Robot. Res. 5:(3):10119
    [Crossref] [Google Scholar]
  16. 16.
    Wensing PM, Niemeyer G, Slotine JJE. 2023.. A geometric characterization of observability in inertial parameter identification. . arXiv:1711.03896 [cs.RO]
  17. 17.
    Mayeda H, Yoshida K, Osuka K. 1988.. Base parameters of manipulator dynamic models. . In 1988 IEEE International Conference on Robotics and Automation 3, pp. 136772 Piscataway, NJ:: IEEE
    [Google Scholar]
  18. 18.
    Gautier M, Khalil W. 1988.. A direct determination of minimum inertial parameters of robots. . In 1988 IEEE International Conference on Robotics and Automation 3, pp. 168287 Piscataway, NJ:: IEEE
    [Google Scholar]
  19. 19.
    Khalil W, Kleinfinger JF. 1987.. Minimum operations and minimum parameters of the dynamic models of tree structure robots. . IEEE J. Robot. Autom. 3:(6):51726
    [Crossref] [Google Scholar]
  20. 20.
    Ros J, Iriarte X, Mata V. 2012.. 3D inertia transfer concept and symbolic determination of the base inertial parameters. . Mech. Mach. Theory 49::28497
    [Crossref] [Google Scholar]
  21. 21.
    Gautier M. 1991.. Numerical calculation of the base inertial parameters of robots. . J. Robot. Syst. 8:(4):485506
    [Crossref] [Google Scholar]
  22. 22.
    Van Huffel S, Vandewalle J. 1991.. The Total Least Squares Problem: Computational Aspects and Analysis. Philadelphia:: Soc. Ind. Appl. Math.
    [Google Scholar]
  23. 23.
    Janot A, Vandanjon PO, Gautier M. 2013.. A generic instrumental variable approach for industrial robot identification. . IEEE Trans. Control Syst. Technol. 22:(1):13245
    [Crossref] [Google Scholar]
  24. 24.
    Janot A, Vandanjon PO, Gautier M. 2009.. Using robust regressions and residual analysis to verify the reliability of LS estimation: application in robotics. . In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 196267 Piscataway, NJ:: IEEE
    [Google Scholar]
  25. 25.
    Ramdani N, Poignet P. 2005.. Robust dynamic experimental identification of robots with set membership uncertainty. . IEEE/ASME Trans. Mechatron. 10:(2):25356
    [Crossref] [Google Scholar]
  26. 26.
    Gevers M. 2005.. Identification for control: from the early achievements to the revival of experiment design. . Eur. J. Control 11:(4–5):33552
    [Crossref] [Google Scholar]
  27. 27.
    Leboutet Q, Roux J, Janot A, Guadarrama-Olvera JR, Cheng G. 2021.. Inertial parameter identification in robotics: a survey. . Appl. Sci. 11:(9):4303
    [Crossref] [Google Scholar]
  28. 28.
    Ayusawa K, Venture G, Nakamura Y. 2014.. Identifiability and identification of inertial parameters using the underactuated base-link dynamics for legged multibody systems. . Int. J. Robot. Res. 33:(3):44668
    [Crossref] [Google Scholar]
  29. 29.
    Venture G, Ayusawa K, Nakamura Y. 2008.. Motion capture based identification of the human body inertial parameters. . In 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 457578 Piscataway, NJ:: IEEE
    [Google Scholar]
  30. 30.
    Ogawa Y, Venture G, Ott C. 2014.. Dynamic parameters identification of a humanoid robot using joint torque sensors and/or contact forces. . In 2014 IEEE-RAS International Conference on Humanoid Robots, pp. 45762 Piscataway, NJ:: IEEE
    [Google Scholar]
  31. 31.
    Del Prete A, Mansard N. 2016.. Robustness to joint-torque-tracking errors in task-space inverse dynamics. . IEEE Trans. Robot. 32:(5):1091105
    [Crossref] [Google Scholar]
  32. 32.
    Sousa CD, Cortesao R. 2014.. Physical feasibility of robot base inertial parameter identification: a linear matrix inequality approach. . Int. J. Robot. Res. 33:(6):93144
    [Crossref] [Google Scholar]
  33. 33.
    Traversaro S, Brossette S, Escande A, Nori F. 2016.. Identification of fully physical consistent inertial parameters using optimization on manifolds. . In 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 544651 Piscataway, NJ:: IEEE
    [Google Scholar]
  34. 34.
    Wensing PM, Kim S, Slotine JJE. 2017.. Linear matrix inequalities for physically consistent inertial parameter identification: a statistical perspective on the mass distribution. . IEEE Robot. Autom. Lett. 3:(1):6067
    [Crossref] [Google Scholar]
  35. 35.
    Jovic J, Escande A, Ayusawa K, Yoshida E, Kheddar A, Venture G. 2016.. Humanoid and human inertia parameter identification using hierarchical optimization. . IEEE Trans. Robot. 32:(3):72635
    [Crossref] [Google Scholar]
  36. 36.
    Ayusawa K, Venture G, Nakamura Y. 2011.. Real-time implementation of physically consistent identification of human body segments. . In 2011 IEEE International Conference on Robotics and Automation, pp. 628287 Piscataway, NJ:: IEEE
    [Google Scholar]
  37. 37.
    Fazeli N, Kolbert R, Tedrake R, Rodriguez A. 2017.. Parameter and contact force estimation of planar rigid-bodies undergoing frictional contact. . Int. J. Robot. Res. 36:(13–14):143754
    [Crossref] [Google Scholar]
  38. 38.
    Kolev S, Todorov E. 2015.. Physically consistent state estimation and system identification for contacts. . In 2015 IEEE-RAS 15th International Conference on Humanoid Robots, pp. 103643 Piscataway, NJ:: IEEE
    [Google Scholar]
  39. 39.
    Jatavallabhula KM, Macklin M, Golemo F, Voleti V, Petrini L, et al. 2021.. gradSim: differentiable simulation for system identification and visuomotor control. . In The Ninth International Conference on Learning Representations. La Jolla, CA: Int. Conf. Learn. Represent. https://iclr.cc/virtual/2021/poster/3082
    [Google Scholar]
  40. 40.
    Hu Y, Anderson L, Li TM, Sun Q, Carr N, et al. 2020.. DiffTaichi: differentiable programming for physical simulation. . In The Eighth International Conference on Learning Representations. La Jolla, CA: Int. Conf. Learn. Represent. https://iclr.cc/virtual_2020/poster_B1eB5xSFvr.html
    [Google Scholar]
  41. 41.
    Xu J, Chen T, Zlokapa L, Foshey M, Matusik W, et al. 2021.. An end-to-end differentiable framework for contact-aware robot design. . In Robotics: Science and Systems XVII, ed. D Shell, M Toussaint, MA Hsieh, pap. 8. N.p.: Robot. Sci. Syst. Found.
    [Google Scholar]
  42. 42.
    Degrave J, Hermans M, Dambre J, Wyffels F. 2019.. A differentiable physics engine for deep learning in robotics. . Front. Neurorobot. 13::6
    [Crossref] [Google Scholar]
  43. 43.
    Hahn D, Banzet P, Bern JM, Coros S. 2019.. Real2Sim: visco-elastic parameter estimation from dynamic motion. . ACM Trans. Graph. 38:(6):236
    [Crossref] [Google Scholar]
  44. 44.
    Geilinger M, Hahn D, Zehnder J, Bächer M, Thomaszewski B, Coros S. 2020.. ADD: analytically differentiable dynamics for multi-body systems with frictional contact. . ACM Trans. Graph. 39:(6):190
    [Crossref] [Google Scholar]
  45. 45.
    Werling K, Omens D, Lee J, Exarchos I, Liu CK. 2021.. Fast and feature-complete differentiable physics engine for articulated rigid bodies with contact constraints. . In Robotics: Science and Systems XVII, ed. DA Shell, M Toussaint, MA Hsieh, pap. 34. N.p. : Robot. Sci. Syst. Found.
    [Google Scholar]
  46. 46.
    Suh HJ, Simchowitz M, Zhang K, Tedrake R. 2022.. Do differentiable simulators give better policy gradients?. In Proceedings of the 39th International Conference on Machine Learning, ed. K Chaudhuri, S Jegelka, L Song, C Szepesvari, G Niu, S Sabatopp , pp. 2066896 Proc. Mach. Learn. Res. 162. N.p. : PMLR
    [Google Scholar]
  47. 47.
    Antonova R, Yang J, Jatavallabhula KM, Bohg J. 2023.. Rethinking optimization with differentiable simulation from a global perspective. . In Proceedings of the 6th Conference on Robot Learning, ed. K Liu, D Kulic, J Ichnowski , pp. 27686 Proc. Mach. Learn. Res. 205. N.p. : PMLR
    [Google Scholar]
  48. 48.
    Lidec QL, Jallet W, Montaut L, Laptev I, Schmid C, Carpentier J. 2023.. Contact models in robotics: a comparative analysis. . arXiv:2304.06372 [cs.RO]
  49. 49.
    Li W, Slotine JJE. 1989.. An indirect adaptive robot controller. . Syst. Control Lett. 12:(3):25966
    [Crossref] [Google Scholar]
  50. 50.
    Yoshida K, Osuka K, Mayeda H, Ono T. 1996.. When is the set of base-parameter values physically impossible?. J. Robot. Soc. Jpn. 14:(1):12230
    [Crossref] [Google Scholar]
  51. 51.
    Yoshida K, Khalil W. 2000.. Verification of the positive definiteness of the inertial matrix of manipulators using base inertial parameters. . Int. J. Robot. Res. 19:(5):498510
    [Crossref] [Google Scholar]
  52. 52.
    Lynch KM, Park FC. 2017.. Modern Robotics. Cambridge, UK:: Cambridge Univ. Press
    [Google Scholar]
  53. 53.
    Wittenburg J. 2008.. Dynamics of Multibody Systems. Berlin:: Springer, 2nd ed.
    [Google Scholar]
  54. 54.
    Todorov E, Erez T, Tassa Y. 2012.. MuJoCo: a physics engine for model-based control. . In 2012 IEEE/RSJ international conference on intelligent robots and systems, pp. 502633 Piscataway, NJ:: IEEE
    [Google Scholar]
  55. 55.
    Lee T, Park FC. 2018.. A geometric algorithm for robust multibody inertial parameter identification. . IEEE Robot. Autom. Lett. 3:(3):245562
    [Crossref] [Google Scholar]
  56. 56.
    Moakher M. 2005.. A differential geometric approach to the geometric mean of symmetric positive-definite matrices. . SIAM J. Matrix Anal. Appl. 26:(3):73547
    [Crossref] [Google Scholar]
  57. 57.
    Lee T, Wensing PM, Park FC. 2019.. Geometric robot dynamic identification: a convex programming approach. . IEEE Trans. Robot. 36:(2):34865
    [Crossref] [Google Scholar]
  58. 58.
    Lee T. 2019.. Geometric methods for dynamic model-based identification and control of multibody systems. PhD Thesis , Seoul Natl. Univ., Seoul, South Korea:
    [Google Scholar]
  59. 59.
    Lee T, Lee BD, Park FC. 2021.. Optimal excitation trajectories for mechanical systems identification. . Automatica 131::109773
    [Crossref] [Google Scholar]
  60. 60.
    Presse C, Gautier M. 1992.. Bayesian estimation of inertial parameters of robots. . In 1992 IEEE International Conference on Robotics and Automation 1, pp. 36465 Piscataway, NJ:: IEEE
    [Google Scholar]
  61. 61.
    Boffi NM, Slotine JJE. 2021.. Implicit regularization and momentum algorithms in nonlinearly parameterized adaptive control and prediction. . Neural Comput. 33:(3):590673
    [Crossref] [Google Scholar]
  62. 62.
    Lee T, Kwon J, Park FC. 2018.. A natural adaptive control law for robot manipulators. . In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Piscataway, NJ:: IEEE. http://doi.org/10.1109/IROS.2018.8593727
    [Crossref] [Google Scholar]
  63. 63.
    Zeng A, Song S, Lee J, Rodriguez A, Funkhouser T. 2020.. TossingBot: learning to throw arbitrary objects with residual physics. . IEEE Trans. Robot. 36:(4):130719
    [Crossref] [Google Scholar]
  64. 64.
    Golemo F, Taiga AA, Courville A, Oudeyer PY. 2018.. Sim-to-real transfer with neural-augmented robot simulation. . In Proceedings of the 2nd Conference on Robot Learning, ed. A Billard, A Dragan, J Peters, J Morimoto , pp. 73443 Proc. Mach. Learn. Res. 87. N.p. : PMLR
    [Google Scholar]
  65. 65.
    Heiden E, Millard D, Coumans E, Sheng Y, Sukhatme GS. 2021.. NeuralSim: augmenting differentiable simulators with neural networks. . In 2021 IEEE International Conference on Robotics and Automation, pp. 947481 Piscataway, NJ:: IEEE
    [Google Scholar]
  66. 66.
    Ajay A, Wu J, Fazeli N, Bauza M, Kaelbling LP, et al. 2018.. Augmenting physical simulators with stochastic neural networks: case study of planar pushing and bouncing. . In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 306673 Piscataway, NJ:: IEEE
    [Google Scholar]
  67. 67.
    Nguyen-Tuong D, Peters J. 2011.. Model learning for robot control: a survey. . Cogn. Process. 12::31940
    [Crossref] [Google Scholar]
  68. 68.
    Marsden JE, West M. 2001.. Discrete mechanics and variational integrators. . Acta Numer. 10::357514
    [Crossref] [Google Scholar]
  69. 69.
    Lee J, Liu CK, Park FC, Srinivasa SS. 2020.. A linear-time variational integrator for multibody systems. . In Algorithmic Foundations of Robotics XII, ed. K Goldberg, P Abbeel, K Bekris, L Miller , pp. 35267 Cham, Switz.:: Springer
    [Google Scholar]
  70. 70.
    Kim M, Lee Y, Lee Y, Lee D. 2017.. Haptic rendering and interactive simulation using passive midpoint integration. . Int. J. Robot. Res. 36:(12):134162
    [Crossref] [Google Scholar]
  71. 71.
    Spong MW. 1996.. Energy based control of a class of underactuated mechanical systems. . IFAC Proc. 29:(1):282832
    [Crossref] [Google Scholar]
  72. 72.
    Spong MW. 2022.. An historical perspective on the control of robotic manipulators. . Annu. Rev. Control Robot. Auton. Syst. 5::131
    [Crossref] [Google Scholar]
  73. 73.
    Lutter M, Ritter C, Peters J. 2019.. Deep Lagrangian networks: using physics as model prior for deep learning. . In The Seventh International Conference on Learning Representations. La Jolla, CA: Int. Conf. Learn. Represent. https://openreview.net/forum?id=BklHpjCqKm
    [Google Scholar]
  74. 74.
    Lutter M, Listmann K, Peters J. 2019.. Deep Lagrangian networks for end-to-end learning of energy-based control for under-actuated systems. . In 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 771825 Piscataway, NJ:: IEEE
    [Google Scholar]
  75. 75.
    Zhong YD, Dey B, Chakraborty A. 2021.. Extending Lagrangian and Hamiltonian neural networks with differentiable contact models. . In Advances in Neural Information Processing Systems 34, ed. M Ranzato, A Beygelzimer, Y Dauphin, PS Liang, J Wortman Vaughan , pp. 2191022 Red Hook, NY:: Curran
    [Google Scholar]
  76. 76.
    Johanastrom K, Canudas-De-Wit C. 2008.. Revisiting the LuGre friction model. . IEEE Control Syst. Mag. 28:(6):10114
    [Crossref] [Google Scholar]
  77. 77.
    Yoon J, Lee M, Son D, Lee D. 2022.. Fast and accurate data-driven simulation framework for contact-intensive tight-tolerance robotic assembly tasks. . arXiv:2202.13098 [cs.RO]
  78. 78.
    Jiang Y, Sun J, Liu CK. 2022.. Data-augmented contact model for rigid body simulation. . In Proceedings of the 4th Annual Learning for Dynamics and Control Conference, ed. R Firoozi, N Mehr, E Yel, R Antonova, J Bohg , et al., pp. 37890 Proc. Mach. Learn. Res. 168. N.p. : PMLR
    [Google Scholar]
  79. 79.
    Pfrommer S, Halm M, Posa M. 2021.. ContactNets: learning discontinuous contact dynamics with smooth, implicit representations. . In Proceedings of the 2020 Conference on Robot Learning, ed. J Kober, F Ramos, C Tomlin , pp. 227991 Proc. Mach. Learn. Res. 155. N.p. : PMLR
    [Google Scholar]
  80. 80.
    Le Cleac'h S, Yu HX, Guo M, Howell T, Gao R, et al. 2023.. Differentiable physics simulation of dynamics-augmented neural objects. . IEEE Robot. Autom. Lett. 8:(5):278087
    [Crossref] [Google Scholar]
  81. 81.
    Mason MT. 2018.. Toward robotic manipulation. . Annu. Rev. Control Robot. Auton. Syst. 1::128
    [Crossref] [Google Scholar]
  82. 82.
    Sanchez-Gonzalez A, Heess N, Springenberg JT, Merel J, Riedmiller M, et al. 2018.. Graph networks as learnable physics engines for inference and control. . In Proceedings of the 35th International Conference on Machine Learning, ed. J Dy, A Krause , pp. 447079 Proc. Mach. Learn. Res. 80. N.p. : PMLR
    [Google Scholar]
  83. 83.
    Battaglia P, Pascanu R, Lai M, Jimenez Rezende D, Kavukcuoglu K. 2016.. Interaction networks for learning about objects, relations and physics. . In Advances in Neural Information Processing Systems 29, ed. D Lee, M Sugiyama, U Luxburg, I Guyon, R Garnett , pp. 450917 Red Hook, NY:: Curran
    [Google Scholar]
  84. 84.
    Allen KR, Guevara TL, Rubanova Y, Stachenfeld K, Sanchez-Gonzalez A, et al. 2023.. Graph network simulators can learn discontinuous, rigid contact dynamics. . In Proceedings of the 6th Conference on Robot Learning, ed. K Liu, D Kulic, J Ichnowski , pp. 115767 Proc. Mach. Learn. Res. 205. N.p. : PMLR
    [Google Scholar]
  85. 85.
    Zhu X, Wang D, Biza O, Su G, Walters R, Platt R. 2022.. Sample efficient grasp learning using equivariant models. . In Robotics: Science and Systems XVIII, ed. K Hauser, D Shell, S Huang, pap. 71. N.p. : Robot. Sci. Syst. Found.
    [Google Scholar]
  86. 86.
    Kim S, Lim B, Lee Y, Park FC. 2023.. SE(2)-equivariant pushing dynamics models for tabletop object manipulations. . In Proceedings of the 6th Conference on Robot Learning, ed. K Liu, D Kulic, J Ichnowski , pp. 42736 Proc. Mach. Learn. Res. 205. N.p. : PMLR
    [Google Scholar]
  87. 87.
    Han J, Huang W, Ma H, Li J, Tenenbaum J, Gan C. 2022.. Learning physical dynamics with subequivariant graph neural networks. . In Advances in Neural Information Processing Systems 34, ed. M Ranzato, A Beygelzimer, Y Dauphin, PS Liang, J Wortman Vaughan , pp. 2191022 Red Hook, NY:: Curran
    [Google Scholar]
  88. 88.
    Lee J, Lee J, Bandyopadhyay T, Sentis L. 2023.. Sample efficient dynamics learning for symmetrical legged robots: leveraging physics invariance and geometric symmetries. . In 2023 IEEE International Conference on Robotics and Automation, pp. 29953001 Piscataway, NJ:: IEEE
    [Google Scholar]
  89. 89.
    Richards SM, Azizan N, Slotine JJE, Pavone M. 2021.. Adaptive-control-oriented meta-learning for nonlinear systems. . In Robotics: Science and Systems XVII, ed. D Shell, M Toussaint, MA Hsieh, pap. 56. N.p. : Robot. Sci. Syst. Found.
    [Google Scholar]
  90. 90.
    Singh S, Richards SM, Sindhwani V, Slotine JJE, Pavone M. 2021.. Learning stabilizable nonlinear dynamics with contraction-based regularization. . Int. J. Robot. Res. 40:(10–11):112350
    [Crossref] [Google Scholar]
/content/journals/10.1146/annurev-control-061523-102310
Loading
/content/journals/10.1146/annurev-control-061523-102310
Loading

Data & Media loading...

  • Article Type: Review Article
This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error