1932

Abstract

Recent successes in the field of machine learning, as well as the availability of increased sensing and computational capabilities in modern control systems, have led to a growing interest in learning and data-driven control techniques. Model predictive control (MPC), as the prime methodology for constrained control, offers a significant opportunity to exploit the abundance of data in a reliable manner, particularly while taking safety constraints into account. This review aims at summarizing and categorizing previous research on learning-based MPC, i.e., the integration or combination of MPC with learning methods, for which we consider three main categories. Most of the research addresses learning for automatic improvement of the prediction model from recorded data. There is, however, also an increasing interest in techniques to infer the parameterization of the MPC controller, i.e., the cost and constraints, that lead to the best closed-loop performance. Finally, we discuss concepts that leverage MPC to augment learning-based controllers with constraint satisfaction properties.

Loading

Article metrics loading...

/content/journals/10.1146/annurev-control-090419-075625
2020-05-03
2024-04-21
Loading full text...

Full text loading...

/deliver/fulltext/control/3/1/annurev-control-090419-075625.html?itemId=/content/journals/10.1146/annurev-control-090419-075625&mimeType=html&fmt=ahah

Literature Cited

  1. 1. 
    Morari M, Lee JH. 1999. Model predictive control: past, present and future. Comput. Chem. Eng. 23:667–82
    [Google Scholar]
  2. 2. 
    Darby ML, Nikolaou M 2012. MPC: current practice and challenges. Control Eng. Pract. 20:328–42
    [Google Scholar]
  3. 3. 
    Bemporad A, Morari M 1999. Robust model predictive control: a survey. Robustness in Identification and Control A Garulli, A Tesi207–26 London: Springer
    [Google Scholar]
  4. 4. 
    Mesbah A 2016. Stochastic model predictive control: an overview and perspectives for future research. IEEE Control Syst. Mag. 36:630–44
    [Google Scholar]
  5. 5. 
    Lee JH, Lee KS 2007. Iterative learning control applied to batch processes: an overview. Control Eng. Pract. 15:1306–18
    [Google Scholar]
  6. 6. 
    Cueli JR, Bordons C 2008. Iterative nonlinear model predictive control. Stability, robustness and applications. Control Eng. Pract. 16:1023–34
    [Google Scholar]
  7. 7. 
    Parisini T, Zoppoli R 1995. A receding-horizon regulator for nonlinear systems and a neural approximation. Automatica 31:1443–51
    [Google Scholar]
  8. 8. 
    Domahidi A, Zeilinger MN, Morari M, Jones CN 2011. Learning a feasible and stabilizing explicit model predictive control law by robust optimization. 2011 50th IEEE Conference on Decision and Control and European Control Conference513–19 Piscataway, NJ: IEEE
    [Google Scholar]
  9. 9. 
    Lucia S, Karg B 2018. A deep learning-based approach to robust nonlinear model predictive control. 6th IFAC Conference on Nonlinear Model Predictive Control: NMPC 2018511–16 IFAC-PapersOnLine 51(20). Amsterdam: Elsevier
    [Google Scholar]
  10. 10. 
    Hertneck M, Köhler J, Trimpe S, Allgöwer F 2018. Learning an approximate model predictive controller with guarantees. IEEE Control Syst. Lett. 2:543–48
    [Google Scholar]
  11. 11. 
    Wittenmark B 1995. Adaptive dual control methods: an overview. 5th IFAC Symposium on Adaptive Systems in Control and Signal Processing67–72 IFAC Proc. Vol. 28(13). Amsterdam: Elsevier
    [Google Scholar]
  12. 12. 
    Mesbah A 2018. Stochastic model predictive control with active uncertainty learning: a survey on dual control. Annu. Rev. Control 45:107–17
    [Google Scholar]
  13. 13. 
    Campi MC, Garatti S 2018. Introduction to the Scenario Approach Philadelphia: Soc. Ind. Appl. Math.
  14. 14. 
    Fagiano L, Schildbach G, Tanaskovic M, Morari M 2015. Scenario and adaptive model predictive control of uncertain systems. 5th IFAC Conference on Nonlinear Model Predictive Control: NMPC 2015352–59 IFAC-PapersOnLine 48(23) Amsterdam: Elsevier
    [Google Scholar]
  15. 15. 
    Rosolia U, Zhang X, Borrelli F 2018. Data-driven predictive control for autonomous systems. Annu. Rev. Control Robot. Auton. Syst. 1:259–86
    [Google Scholar]
  16. 16. 
    Recht B 2019. A tour of reinforcement learning: the view from continuous control. Annu. Rev. Control Robot. Auton. Syst. 2:253–79
    [Google Scholar]
  17. 17. 
    Bertsekas DP 2012. Dynamic Programming and Optimal Control 2 Approximate Dynamic Programming Belmont, MA: Athena Sci. 4th ed.
  18. 18. 
    Bertsekas DP 2017. Dynamic Programming and Optimal Control Vol. 1. Belmont, MA: Athena Sci. 4th ed.
  19. 19. 
    Mayne DQ, Rawlings JB, Rao CV, Scokaert POM 2000. Constrained model predictive control: stability and optimality. Automatica 36:789–814
    [Google Scholar]
  20. 20. 
    Rawlings JB, Mayne DQ, Diehl MM 2017. Model Predictive Control: Theory, Computation, and Design Madison, WI: Nob Hill. 2nd ed.
  21. 21. 
    Bishop C 2006. Pattern Recognition and Machine Learning New York: Springer
  22. 22. 
    Piché S, Sayyar-Rodsari B, Johnson D, Gerules M 2000. Nonlinear model predictive control using neural networks. IEEE Control Syst. Mag. 20:353–62
    [Google Scholar]
  23. 23. 
    Nagabandi A, Clavera I, Liu S, Fearing RS, Abbeel P 2019. Learning to adapt in dynamic, real-world environments through meta-reinforcement learning Paper presented at the Seventh International Conference on Learning Representations New Orleans, LA: May 6–9. https://openreview.net/forum?id=HyztsoC5Y7
  24. 24. 
    Yang H, Li S 2015. A data-driven predictive controller design based on reduced Hankel matrix. 2015 10th Asian Control Conference Piscataway, NJ: IEEE. https://doi.org/10.1109/ASCC.2015.7244723
    [Crossref] [Google Scholar]
  25. 25. 
    Coulson J, Lygeros J, Dörfler F 2019. Data-enabled predictive control: in the shallows of the DeePC. 2019 18th European Control Conference307–12 Piscataway, NJ: IEEE
    [Google Scholar]
  26. 26. 
    Feldbaum AA 1960. Dual control theory. I. Avtom. Telemekhanika 21:1240–49
    [Google Scholar]
  27. 27. 
    Feldbaum AA 1960. Dual control theory. II. Avtom. Telemekhanika 21:1453–64
    [Google Scholar]
  28. 28. 
    Heirung TAN, Foss B, Ydstie BE 2015. MPC-based dual control with online experiment design. J. Process Control 32:64–76
    [Google Scholar]
  29. 29. 
    Alpcan T, Shames I 2015. An information-based learning approach to dual control. IEEE Trans. Neural Netw. Learn. Syst. 26:2736–48
    [Google Scholar]
  30. 30. 
    Genceli H, Nikolaou M 1996. New approach to constrained predictive control with simultaneous model identification. AIChE J. 42:2857–68
    [Google Scholar]
  31. 31. 
    Marafioti G, Bitmead RR, Hovd M 2014. Persistently exciting model predictive control. Int. J. Adapt. Control Signal Process. 28:536–52
    [Google Scholar]
  32. 32. 
    Hanssen KG, Foss B 2015. Scenario based implicit dual model predictive control. 5th IFAC Conference on Nonlinear Model Predictive Control: NMPC 2015416–21 IFAC-PapersOnLine 48(23). Amsterdam: Elsevier
    [Google Scholar]
  33. 33. 
    Thangavel S, Lucia S, Paulen R, Engell S 2018. Dual robust nonlinear model predictive control: a multi-stage approach. J. Process Control 72:39–51
    [Google Scholar]
  34. 34. 
    Lee JM, Lee JH 2009. An approximate dynamic programming based approach to dual adaptive control. J. Process Control 19:859–64
    [Google Scholar]
  35. 35. 
    Heirung TAN, Ydstie BE, Foss B 2017. Dual adaptive model predictive control. Automatica 80:340–48
    [Google Scholar]
  36. 36. 
    Klenske ED, Hennig P 2016. Dual control for approximate Bayesian reinforcement learning. J. Mach. Learn. Res. 17:1–30
    [Google Scholar]
  37. 37. 
    Aswani A, Gonzalez H, Sastry SS, Tomlin CJ 2013. Provably safe and robust learning-based model predictive control. Automatica 49:1216–26
    [Google Scholar]
  38. 38. 
    Bouffard P, Aswani A, Tomlin CJ 2012. Learning-based model predictive control on a quadrotor: onboard implementation and experimental results. 2012 IEEE International Conference on Robotics and Automation279–84 Piscataway, NJ: IEEE
    [Google Scholar]
  39. 39. 
    Aswani A, Bouffard P, Tomlin CJ 2012. Extensions of learning-based model predictive control for real-time application to a quadrotor helicopter. 2012 American Control Conference4661–66 Piscataway, NJ: IEEE
    [Google Scholar]
  40. 40. 
    Aswani A, Master N, Taneja J, Culler D, Tomlin CJ 2012. Reducing transient and steady state electricity consumption in HVAC using learning-based model-predictive control. Proc. IEEE 100:240–53
    [Google Scholar]
  41. 41. 
    Aswani A, Master N, Taneja J, Krioukov A, Culler D, Tomlin CJ 2012. Energy-efficient building HVAC control using hybrid system LBMPC. 4th IFAC Conference on Nonlinear Model Predictive Control496–501 IFAC Proc. Vol. 45(17). Amsterdam: Elsevier
    [Google Scholar]
  42. 42. 
    Milanese M, Vicino A 1991. Optimal estimation theory for dynamic systems with set membership uncertainty: an overview. Automatica 27:997–1009
    [Google Scholar]
  43. 43. 
    Milanese M, Novara C 2004. Set membership identification of nonlinear systems. Automatica 40:957–75
    [Google Scholar]
  44. 44. 
    Veres SM, Messaoud H, Norton JP 1999. Limited-complexity model-unfalsifying adaptive tracking-control. Int. J. Control 72:1417–26
    [Google Scholar]
  45. 45. 
    Tanaskovic M, Fagiano L, Smith R, Morari M 2014. Adaptive receding horizon control for constrained MIMO systems. Automatica 50:3019–29
    [Google Scholar]
  46. 46. 
    Tanaskovic M, Sturzenegger D, Smith R, Morari M 2017. Robust adaptive model predictive building climate control. 20th IFAC World Congress1871–76 IFAC-PapersOnLine 50(1). Amsterdam: Elsevier
    [Google Scholar]
  47. 47. 
    Tanaskovic M, Fagiano L, Gligorovski V 2019. Adaptive model predictive control for linear time varying MIMO systems. Automatica 105:237–45
    [Google Scholar]
  48. 48. 
    Bujarbaruah M, Zhang X, Borrelli F 2018. Adaptive MPC with chance constraints for FIR systems. arXiv:1804.09790 [cs.SY]
    [Google Scholar]
  49. 49. 
    Bujarbaruah M, Zhang X, Rosolia U, Borrelli F 2018. Adaptive MPC for iterative tasks. 2018 IEEE Conference on Decision and Control6322–27 Piscataway, NJ: IEEE
    [Google Scholar]
  50. 50. 
    Terzi E, Fagiano L, Farina M, Scattolini R 2018. Learning multi-step prediction models for receding horizon control. 2018 European Control Conference1335–40 Piscataway, NJ: IEEE
    [Google Scholar]
  51. 51. 
    Terzi E, Farina M, Fagiano L, Scattolini R 2018. Robust predictive control with data-based multi-step prediction models. 2018 European Control Conference1710–15 Piscataway, NJ: IEEE
    [Google Scholar]
  52. 52. 
    Terzi E, Fagiano L, Farina M, Scattolini R 2019. Learning-based predictive control for linear systems: a unitary approach. Automatica 108:108473
    [Google Scholar]
  53. 53. 
    Di Cairano S 2016. Indirect adaptive model predictive control for linear systems with polytopic uncertainty. 2016 American Control Conference3570–75 Piscataway, NJ: IEEE
    [Google Scholar]
  54. 54. 
    Zhou J, Di Cairano S, Danielson C 2017. Indirect adaptive MPC for output tracking of uncertain linear polytopic systems. 2017 American Control Conference3054–59 Piscataway, NJ: IEEE
    [Google Scholar]
  55. 55. 
    Lorenzen M, Allgöwer F, Cannon M 2017. Adaptive model predictive control with robust constraint satisfaction. 20th IFAC World Congress3313–18 IFAC-PapersOnLine 50(1). Amsterdam: Elsevier
    [Google Scholar]
  56. 56. 
    Lorenzen M, Cannon M, Allgöwer F 2019. Robust MPC with recursive model update. Automatica 103:461–71
    [Google Scholar]
  57. 57. 
    Fukushima H, Kim TH, Sugie T 2007. Adaptive model predictive control for a class of constrained linear systems based on the comparison model. Automatica 43:301–8
    [Google Scholar]
  58. 58. 
    Kim TH, Sugie T 2008. Adaptive receding horizon predictive control for constrained discrete-time linear systems with parameter uncertainties. Int. J. Control 81:62–73
    [Google Scholar]
  59. 59. 
    Adetola V, DeHaan D, Guay M 2009. Adaptive model predictive control for constrained nonlinear systems. Syst. Control Lett. 58:320–26
    [Google Scholar]
  60. 60. 
    Adetola V, Guay M 2011. Robust adaptive MPC for constrained uncertain nonlinear systems. Int. J. Adapt. Control Signal Process. 25:155–67
    [Google Scholar]
  61. 61. 
    Gonçalves GAA, Guay M 2016. Robust discrete-time set-based adaptive predictive control for nonlinear systems. J. Process Control 39:111–22
    [Google Scholar]
  62. 62. 
    Beliakov G 2006. Interpolation of Lipschitz functions. J. Comput. Appl. Math. 196:20–44
    [Google Scholar]
  63. 63. 
    Calliess JP 2014. Conservative decision-making and inference in uncertain dynamical systems PhD Thesis, Univ. Oxford, Oxford, UK
  64. 64. 
    Canale M, Fagiano L, Signorile MC 2011. Robust design of predictive controllers using set membership identified models. 18th IFAC World Congress13414–19 IFAC Proc. Vol. 44(1). Amsterdam: Elsevier
    [Google Scholar]
  65. 65. 
    Canale M, Fagiano L, Signorile MC 2014. Nonlinear model predictive control from data: a set membership approach. Int. J. Robust Nonlinear Control 24:123–39
    [Google Scholar]
  66. 66. 
    Limon D, Calliess J, Maciejowski JM 2017. Learning-based nonlinear model predictive control. 20th IFAC World Congress7769–76 IFAC-PapersOnLine 50(1). Amsterdam: Elsevier
    [Google Scholar]
  67. 67. 
    Calliess JP, Roberts S, Rasmussen C, Maciejowski J 2018. Nonlinear set membership regression with adaptive hyper-parameter estimation for online learning and control. 2018 European Control Conference Piscataway, NJ: IEEE https://doi.org/10.23919/ECC.2018.8550439
    [Crossref] [Google Scholar]
  68. 68. 
    Manzano JM, Limon D, de la Peña DM, Calliess J 2018. Robust data-based model predictive control for nonlinear constrained systems. 6th IFAC Conference on Nonlinear Model Predictive Control: NMPC 2018505–10 IFAC-PapersOnLine 51(20). Amsterdam: Elsevier
    [Google Scholar]
  69. 69. 
    Manzano JM, Limón D, de la Peña DM, Calliess J 2019. Output feedback MPC based on smoothed projected kinky inference. IET Control Theory Appl. 13:795–805
    [Google Scholar]
  70. 70. 
    Maddalena ET, Jones CN 2019. Learning non-parametric models with guarantees: a smooth Lipschitz interpolation approach Tech. Rep., École Polytech. Féd. Lausanne, Lausanne, Switz.
  71. 71. 
    Soloperto R, Müller MA, Trimpe S, Allgöwer F 2018. Learning-based robust model predictive control with state-dependent uncertainty. 6th IFAC Conference on Nonlinear Model Predictive Control: NMPC 2018442–47 IFAC-PapersOnLine 51(20). Amsterdam: Elsevier
    [Google Scholar]
  72. 72. 
    Koller T, Berkenkamp F, Turchetta M, Krause A 2018. Learning-based model predictive control for safe exploration. 2018 IEEE Conference on Decision and Control6059–66 Piscataway, NJ: IEEE
    [Google Scholar]
  73. 73. 
    Wabersich KP, Hewing L, Carron A, Zeilinger MN 2019. Probabilistic model predictive safety certification for learning-based control. arXiv:1906.10417 [eess.SY]
    [Google Scholar]
  74. 74. 
    Paulson JA, Santos TLM, Mesbah A 2019. Mixed stochastic-deterministic tube MPC for offset-free tracking in the presence of plant-model mismatch. J. Process Control 83:102–20
    [Google Scholar]
  75. 75. 
    Calafiore G, Campi MC 2005. Uncertain convex programs: randomized solutions and confidence levels. Math. Program. 102:25–46
    [Google Scholar]
  76. 76. 
    Campi MC, Garatti S 2011. A sampling-and-discarding approach to chance-constrained optimization: feasibility and optimality. J. Optim. Theory Appl. 148:257–80
    [Google Scholar]
  77. 77. 
    Desaraju VR, Michael N 2016. Experience-driven predictive control. Proceedings of the 1st International Workshop on Robot Learning and Planning29–37 N.p.: RLP
    [Google Scholar]
  78. 78. 
    Desaraju VR, Spitzer AE, Michael N 2017. Experience-driven predictive control with robust constraint satisfaction under time-varying state uncertainty Robotics: Science and Systems XIII N Amato, S Srinivasa, N Ayanian, S Kuindersma 67. N.p.: Robot. Sci. Syst. Found.
  79. 79. 
    McKinnon CD, Schoellig AP 2019. Learn fast, forget slow: safe predictive control for systems with locally linear actuator dynamics performing repetitive tasks. IEEE Robot. Autom. Lett. 4:2180–87
    [Google Scholar]
  80. 80. 
    Schildbach G, Fagiano L, Frei C, Morari M 2014. The scenario approach for stochastic model predictive control with bounds on closed-loop constraint violations. Automatica 50:3009–18
    [Google Scholar]
  81. 81. 
    Calafiore GC, Fagiano L 2013. Stochastic model predictive control of LPV systems via scenario optimization. Automatica 49:1861–66
    [Google Scholar]
  82. 82. 
    Lorenzen M, Dabbene F, Tempo R, Allgöwer F 2017. Stochastic MPC with offline uncertainty sampling. Automatica 81:176–83
    [Google Scholar]
  83. 83. 
    Hewing L, Zeilinger MN 2019. Scenario-based probabilistic reachable sets for recursively feasible stochastic model predictive control. IEEE Control Syst. Lett 4:450–55
    [Google Scholar]
  84. 84. 
    Di Cairano S, Bernardini D, Bemporad A Kolmanovsky IV. 2014. Stochastic MPC with learning for driver-predictive vehicle control and its application to HEV energy management. IEEE Trans. Control Syst. Technol. 22:1018–31
    [Google Scholar]
  85. 85. 
    Rasmussen CE, Williams CKI 2006. Gaussian Processes for Machine Learning Cambridge, MA: MIT Press
  86. 86. 
    Hewing L, Kabzan J, Zeilinger MN 2019. Cautious model predictive control using Gaussian process regression. IEEE Trans. Control Syst. Technol. In press. https://doi.org/10.1109/TCST.2019.2949757
    [Crossref] [Google Scholar]
  87. 87. 
    Ostafew CJ, Schoellig AP, Barfoot TD 2016. Robust constrained learning-based NMPC enabling reliable mobile robot path tracking. Int. J. Robot. Res. 35:1547–63
    [Google Scholar]
  88. 88. 
    Kamthe S, Deisenroth MP 2018. Data-efficient reinforcement learning with probabilistic model predictive control. Proceedings of the 21st International Conference on Artificial Intelligence and Statistics A Storkey, F Perez-Cruz1701–10 Proc. Mach. Learn. Res. 84. N.p.: PMLR
    [Google Scholar]
  89. 89. 
    Maiworm M, Limon D, Manzano JM, Findeisen R 2018. Stability of Gaussian process learning based output feedback model predictive control. 6th IFAC Conference on Nonlinear Model Predictive Control: NMPC 2018455–61 IFAC-PapersOnLine 51(20). Amsterdam: Elsevier
    [Google Scholar]
  90. 90. 
    Kabzan J, Hewing L, Liniger A, Zeilinger MN 2019. Learning-based model predictive control for autonomous racing. IEEE Robot. Autom. Lett. 4:3363–70
    [Google Scholar]
  91. 91. 
    Kabzan J, Hewing L, Liniger A, Zeilinger MN 2019. MPCC with Gaussian process based model learning for autonomous racing. YouTube Sept. 3. https://www.youtube.com/watch?v=-cdXw1MyTUA
    [Google Scholar]
  92. 92. 
    Kabzan J, Hewing L, Liniger A, Zeilinger MN 2019. Learning-based model predictive control for autonomous racing. YouTube, July 11. https://www.youtube.com/watch?v=bjlT-6KVQ7U
    [Google Scholar]
  93. 93. 
    Quiñonero-Candela J, Rasmussen CE 2005. A unifying view of sparse approximate Gaussian process regression. J. Mach. Learn. Res. 6:1939–59
    [Google Scholar]
  94. 94. 
    Lázaro-Gredilla M, Quiñonero-Candela J, Rasmussen CE, Figueiras-Vidal AR 2010. Sparse spectrum Gaussian process regression. J. Mach. Learn. Res. 11:1865–81
    [Google Scholar]
  95. 95. 
    Carron A, Arcari E, Wermelinger M, Hewing L, Hutter M, Zeilinger MN 2019. Data-driven model predictive control for trajectory tracking with a robotic arm. IEEE Robot. Autom. Lett. 4:3758–65
    [Google Scholar]
  96. 96. 
    Ostafew CJ, Collier J, Schoellig AP, Barfoot TD 2016. Learning-based nonlinear model predictive control to improve vision-based mobile robot path tracking. J. Field Robot. 33:133–52
    [Google Scholar]
  97. 97. 
    Pan Y, Yan X, Theodorou EA, Boots B 2017. Prediction under uncertainty in sparse spectrum Gaussian processes with applications to filtering and control. Proceedings of the 34th International Conference on Machine Learning D Precup, YW Teh2760–68 Proc. Mach. Learn. Res. 70. N.p.: PMLR
    [Google Scholar]
  98. 98. 
    Kocijan J, Murray-Smith R, Rasmussen CE, Girard A 2004. Gaussian process model based predictive control. In Proceedings of the 2004 American Control Conference2214–19 Piscataway, NJ: IEEE
    [Google Scholar]
  99. 99. 
    Klenske ED, Zeilinger MN, Schölkopf B, Hennig P 2016. Gaussian process-based predictive control for periodic error correction. IEEE Trans. Control Syst. Technol. 24:110–21
    [Google Scholar]
  100. 100. 
    Jain A, Nghiem TX, Morari M, Mangharam R 2018. Learning and control using Gaussian processes: towards bridging machine learning and controls for physical systems. Proceedings of the 9th ACM/IEEE International Conference on Cyber-Physical Systems140–49 Piscataway, NJ: IEEE
    [Google Scholar]
  101. 101. 
    Shahriari B, Swersky K, Wang Z, Adams RP, de Freitas N 2016. Taking the human out of the loop: a review of Bayesian optimization. Proc. IEEE 104:148–75
    [Google Scholar]
  102. 102. 
    Berkenkamp F, Schoellig AP, Krause A 2016. Safe controller optimization for quadrotors with Gaussian processes. In 2016 IEEE International Conference on Robotics and Automation491–96 Piscataway, NJ: IEEE
    [Google Scholar]
  103. 103. 
    Neumann-Brosig M, Marco A, Schwarzmann D, Trimpe S 2019. Data-efficient auto-tuning with Bayesian optimization: an industrial control study. IEEE Trans. Control Syst. Technol. In press
    [Google Scholar]
  104. 104. 
    Marco A, Hennig P, Bohg J, Schaal S, Trimpe S 2016. Automatic LQR tuning based on Gaussian process global optimization. 2016 IEEE International Conference on Robotics and Automation270–77 Piscataway, NJ: IEEE
    [Google Scholar]
  105. 105. 
    Fröhlich LP, Klenske ED, Daniel CG, Zeilinger MN 2019. Bayesian optimization for policy search in high-dimensional systems via automatic domain selection. 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems757–64 Piscataway, NJ: IEEE
    [Google Scholar]
  106. 106. 
    Bansal S, Calandra R, Xiao T, Levine S, Tomlin CJ 2017. Goal-driven dynamics learning via Bayesian optimization. 2017 IEEE 56th Annual Conference on Decision and Control5168–73 Piscataway, NJ: IEEE
    [Google Scholar]
  107. 107. 
    Piga D, Forgione M, Formentin S, Bemporad A 2019. Performance-oriented model learning for data-driven MPC design. IEEE Control Syst. Lett. 3:577–82
    [Google Scholar]
  108. 108. 
    Gros S, Zanon M 2020. Data-driven economic NMPC using reinforcement learning. IEEE Trans. Autom. Control 65:636–48
    [Google Scholar]
  109. 109. 
    Blanchini F, Pellegrino FA 2005. Relatively optimal control: the static solution. 16th IFAC World Congress676–81 IFAC Proc. Vol. 38(1). Amsterdam: Elsevier
    [Google Scholar]
  110. 110. 
    Brunner FD, Lazar M, Allgöwer F 2015. Stabilizing model predictive control: on the enlargement of the terminal set. Int. J. Robust Nonlinear Control 25:2646–70
    [Google Scholar]
  111. 111. 
    Rosolia U, Borrelli F 2018. Learning model predictive control for iterative tasks. A data-driven control framework. IEEE Trans. Autom. Control 63:1883–96
    [Google Scholar]
  112. 112. 
    Rosolia U, Zhang X, Borrelli F 2017. Robust learning model predictive control for uncertain iterative tasks: learning from experience. 2017 IEEE 56th Annual Conference on Decision and Control1157–62 Piscataway, NJ: IEEE
    [Google Scholar]
  113. 113. 
    Rosolia U, Borrelli F 2019. Learning how to autonomously race a car: a predictive control approach. arXiv:1901.08184 [cs.SY]
    [Google Scholar]
  114. 114. 
    Priess MC, Conway R, Choi J, Popovich JM, Radcliffe C 2014. Solutions to the inverse LQR problem with application to biological systems analysis. IEEE Trans. Control Syst. Technol. 23:770–77
    [Google Scholar]
  115. 115. 
    Menner M, Zeilinger MN 2018. Convex formulations and algebraic solutions for linear quadratic inverse optimal control problems. 2018 European Control Conference2107–12 Piscataway, NJ: IEEE
    [Google Scholar]
  116. 116. 
    Englert P, Vien NA, Toussaint M 2017. Inverse KKT: learning cost functions of manipulation tasks from demonstrations. Int. J. Robot. Res. 36:1474–88
    [Google Scholar]
  117. 117. 
    Menner M, Worsnop P, Zeilinger MN 2019. Constrained inverse optimal control with application to a human manipulation task. IEEE Trans. Control Syst. Technol. In press
    [Google Scholar]
  118. 118. 
    Aswani A, Shen ZJ, Siddiq A 2018. Inverse optimization with noisy data. Oper. Res. 66:870–92
    [Google Scholar]
  119. 119. 
    Abbeel P, Ng AY 2004. Apprenticeship learning via inverse reinforcement learning. Proceedings of the Twenty-First International Conference on Machine Learning , pap. 1. New York: ACM
    [Google Scholar]
  120. 120. 
    Ziebart BD, Maas A, Bagnell JA, Dey AK 2008. Maximum entropy inverse reinforcement learning. Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence1433–38 Palo Alto, CA: AAAI Press
    [Google Scholar]
  121. 121. 
    Argall BD, Chernova S, Veloso M, Browning B 2009. A survey of robot learning from demonstration. Robot. Auton. Syst. 57:469–83
    [Google Scholar]
  122. 122. 
    Finn C, Levine S, Abbeel P 2016. Guided cost learning: deep inverse optimal control via policy optimization. Proceedings of the 33rd International Conference on Machine Learning MF Balcan, KQ Weinberger 49–58 Proc. Mach. Learn. Res. 48. N.p.: PMLR
    [Google Scholar]
  123. 123. 
    Menner M, Berntorp K, Zeilinger MN, Di Cairano S 2019. Inverse learning for human-adaptive motion planning. 2019 IEEE Conference on Decision and Control Piscataway, NJ: IEEE. Forthcoming
    [Google Scholar]
  124. 124. 
    Chou G, Berenson D, Ozay N 2018. Learning constraints from demonstrations. arXiv:1812.07084 [cs.RO]
    [Google Scholar]
  125. 125. 
    Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, et al 2015. Human-level control through deep reinforcement learning. Nature 518:529–33
    [Google Scholar]
  126. 126. 
    Levine S, Finn C, Darrell T, Abbeel P 2016. End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17:1334–73
    [Google Scholar]
  127. 127. 
    Gillulay JH, Tomlin CJ 2011. Guaranteed safe online learning of a bounded system. 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems2979–84 Piscataway, NJ: IEEE
    [Google Scholar]
  128. 128. 
    Wabersich KP, Zeilinger MN 2018. Safe exploration of nonlinear dynamical systems: a predictive safety filter for reinforcement learning. arXiv:1812.05506 [cs.SY]
    [Google Scholar]
  129. 129. 
    Seto D, Krogh B, Sha L, Chutinan A 1998. The simplex architecture for safe online control system upgrades. Proceedings of the 1998 American Control Conference3504–8 Piscataway, NJ: IEEE
    [Google Scholar]
  130. 130. 
    Wieland P, Allgöwer F 2007. Constructive safety using control barrier functions. 7th IFAC Symposium on Nonlinear Control Systems462–67 IFAC Proc. Vol. 40(12). Amsterdam: Elsevier
    [Google Scholar]
  131. 131. 
    Wieland P, Ebenbauer C, Allgöwer F 2007. Ensuring task-independent safety for multi-agent systems by feedback. 2007 American Control Conference3880–85 Piscataway, NJ: IEEE
    [Google Scholar]
  132. 132. 
    Berkenkamp F, Turchetta M, Schoellig AP, Krause A 2017. Safe model-based reinforcement learning with stability guarantees. Advances in Neural Information Processing Systems 30 I Guyon, UV Luxburg, S Bengio, H Wallach, R Fergus908–18 Red Hook, NY: Curran
    [Google Scholar]
  133. 133. 
    Fisac JF, Akametalu AK, Zeilinger MN, Kaynama S, Gillula J, Tomlin CJ 2019. A general safety framework for learning-based control in uncertain robotic systems. IEEE Trans. Autom. Control 64:2737–52
    [Google Scholar]
  134. 134. 
    Wabersich KP, Zeilinger MN 2018. Scalable synthesis of safety certificates from data with application to learning-based control. 2018 European Control Conference1691–97 Piscataway, NJ: IEEE
    [Google Scholar]
  135. 135. 
    Larsen RB, Carron A, Zeilinger MN 2017. Safe learning for distributed systems with bounded uncertainties. 20th IFAC World Congress2536–42 IFAC-PapersOnLine 50(1). Amsterdam: Elsevier
    [Google Scholar]
  136. 136. 
    Gurriet T, Mote M, Ames AD, Feron E 2018. An online approach to active set invariance. 2018 IEEE Conference on Decision and Control3592–99 Piscataway, NJ: IEEE
    [Google Scholar]
  137. 137. 
    Bastani O 2019. Safe reinforcement learning via online shielding. arXiv:1905.10691 [cs.LG]
    [Google Scholar]
  138. 138. 
    Wabersich KP, Zeilinger MN 2018. Linear model predictive safety certification for learning-based control. 2018 IEEE Conference on Decision and Control7130–35 Piscataway, NJ: IEEE
    [Google Scholar]
/content/journals/10.1146/annurev-control-090419-075625
Loading
/content/journals/10.1146/annurev-control-090419-075625
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