, S0 ?Su one could consider two ?-terms instead of one to derive a less conservative tightening. In the same spirit d(t) could be projected onto S, and the projection incorporated in the scalar products of the left hand-side. For Q(·) ? 0, x(0) 2 could be replaced in (4) by an S0-norm S0x(0) 2 with a surjective S0 ? R N 0 ,N where N0 = dim(S0), Using that x(·) = z0(·)+z1(·) ?

, Definition (19) corresponds to a covering obtained through balls in S

, The reproducing property, K(·, t1)p1, K(·, t2)p2 K = p 2 K(t2, t1)p1, applied to x(·) allows to explicit z. References Ackermann, J, 1985.

N. Aronszajn, Theory of reproducing kernels, Transactions of the American Mathematical Society, vol.68, pp.337-404, 1950.

P. Aubin-frankowski, N. Petit, and Z. Szabó, Kernel regression for vehicle trajectory reconstruction under speed and inter-vehicular distance constraints, IFAC World Congress, 2020.

P. Aubin-frankowski and Z. Szabó, Hard shape-constrained kernel machines, 2020.
URL : https://hal.archives-ouvertes.fr/hal-02625276

T. Bertalan, F. Dietrich, I. Mezi?, and I. G. Kevrekidis, On learning Hamiltonian systems from data, Chaos: An Interdisciplinary Journal of Nonlinear Science, vol.29, issue.12, pp.121107-121108, 2019.

L. Bourdin and E. Trélat, Linear-quadratic optimal sampled-data control problems: Convergence result and Riccati theory, Automatica, vol.79, pp.273-281, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01304197

R. S. Burachik, C. Y. Kaya, and S. N. Majeed, A Duality Approach for Solving Control-Constrained Linear-Quadratic Optimal Control Problems, SIAM Journal on Control and Optimization, vol.52, issue.3, pp.1423-1456, 2014.

F. Chaplais, P. Malisani, and N. Petit, Design of penalty functions for optimal control of linear dynamical systems under state and input constraints, Conference on Decision and Control (CDC), pp.6697-6704, 2011.
URL : https://hal.archives-ouvertes.fr/hal-00676305

A. Chiuso and G. Pillonetto, System Identification: A Machine Learning Perspective, Robotics, and Autonomous Systems, vol.2, issue.1, pp.281-304, 2019.

P. M. Dower, W. M. Mceneaney, and M. Cantoni, Game representations for state constrained continuous time linear regulator problems, 2019.

K. Fujii and Y. Kawahara, Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables, Neural Networks, vol.117, pp.94-103, 2019.

H. Fujioka and H. Kano, Control theoretic B-spline smoothing with constraints on derivatives, pp.2115-2120, 2013.

M. Gerdts and B. Hüpping, Virtual control regularization of state constrained linear quadratic optimal control problems, Computational Optimization and Applications, vol.51, issue.2, pp.867-882, 2012.
URL : https://hal.archives-ouvertes.fr/hal-00724866

D. Giannakis, S. Das, and J. Slawinska, Reproducing kernel Hilbert space compactification of unitary evolution groups, 2019.

L. Grüne and R. Guglielmi, Turnpike properties and strict dissipativity for discrete time linear quadratic optimal control problems, SIAM Journal on Control and Optimization, vol.56, issue.2, pp.1282-1302, 2018.

G. Haddad, Monotone trajectories of differential inclusions and functional differential inclusions with memory, Israel Journal of Mathematics, vol.39, issue.1-2, pp.83-100, 1981.

R. F. Hartl, S. P. Sethi, and R. G. Vickson, A Survey of the Maximum Principles for Optimal Control Problems with State Constraints, SIAM Review, vol.37, issue.2, pp.181-218, 1995.

N. Heckman, The theory and application of penalized methods or Reproducing Kernel Hilbert Spaces made easy, Statistics Surveys, vol.6, issue.0, pp.113-141, 2012.

A. Hermant, Stability analysis of optimal control problems with a second-order state constraint, SIAM Journal on Optimization, vol.20, issue.1, pp.104-129, 2009.
URL : https://hal.archives-ouvertes.fr/inria-00186968

T. Kailath, RKHS approach to detection and estimation problems-I: Deterministic signals in Gaussian noise, IEEE Transactions on Information Theory, vol.17, issue.5, pp.530-549, 1971.

H. Kano and H. Fujioka, B-spline trajectory planning with curvature constraint, 2018 Annual American Control Conference (ACC), pp.1963-1968, 2018.

A. Kojima and M. Morari, LQ control for constrained continuous-time systems, Automatica, vol.40, issue.7, pp.1143-1155, 2004.

M. Egerstedt and C. M. , Control Theoretic Splines: Optimal Control, Statistics, and Path Planning (Princeton Series in Applied Mathematics), 2009.

A. Marco, P. Hennig, S. Schaal, and S. Trimpe, On the design of LQR kernels for efficient controller learning, Conference on Decision and Control (CDC), pp.5193-5200, 2017.

J. Mattingley and S. Boyd, CVXGEN: a code generator for embedded convex optimization, Optimization and Engineering, vol.13, issue.1, pp.1-27, 2012.

T. Mercy, W. Van-loock, and G. Pipeleers, Real-time motion planning in the presence of moving obstacles, European Control Conference (ECC), pp.1586-1591, 2016.

M. Micheli and J. A. Glaunès, Matrix-valued kernels for shape deformation analysis. Geometry, Imaging and Computing, vol.1, issue.1, pp.57-139, 2014.
URL : https://hal.archives-ouvertes.fr/hal-00857313

E. Parzen, Statistical inference on time series by RKHS methods, Proceedings 12th Biennial Seminar, 1970.

G. Pillonetto, F. Dinuzzo, T. Chen, G. D. Nicolao, and L. Ljung, Kernel methods in system identification, machine learning and function estimation: A survey, Automatica, vol.50, issue.3, pp.657-682, 2014.

J. A. Rosenfeld, R. Kamalapurkar, L. F. Gruss, J. , and T. T. , Dynamic Mode Decomposition for Continuous Time Systems with the Liouville Operator, 2019.

B. Schölkopf, R. Herbrich, and A. J. Smola, A generalized representer theorem, Computational Learning Theory (CoLT), pp.416-426, 2001.

B. Schölkopf and A. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, 2002.

L. Schwartz, Sous-espaces hilbertiens d'espaces vectoriels topologiques et noyaux associés (noyaux reproduisants), Journal d'Analyse Mathématique, vol.13, pp.115-256, 1964.

S. Singh, V. Sindhwani, J. Slotine, and M. Pavone, Learning stabilizable dynamical systems via control contraction metrics, Workshop on Algorithmic Foundations of Robotics (WAFR, 2018.

A. Sootla, A. Mauroy, E. , and D. , Optimal control formulation of pulse-based control using Koopman operator, Automatica, vol.91, pp.217-224, 2018.

J. L. Speyer and D. H. Jacobson, Primer on Optimal Control Theory, 2010.

F. Steinke and B. Schölkopf, Kernels, regularization and differential equations, Pattern Recognition, vol.41, issue.11, pp.3271-3286, 2008.

T. Van-keulen, Solution for the continuous-time infinite-horizon linear quadratic regulator subject to scalar state constraints, IEEE Control Systems Letters, vol.4, issue.1, pp.133-138, 2020.

C. Van-loan, Computing integrals involving the matrix exponential, IEEE Transactions on Automatic Control, vol.23, issue.3, pp.395-404, 1978.

R. Vinter, Optimal Control, 1990.
URL : https://hal.archives-ouvertes.fr/inria-00629428

G. Wahba, Spline Models for Observational Data, SIAM, CBMS-NSF Regional Conference Series in Applied Mathematics, 1990.

M. O. Williams, C. W. Rowley, and I. G. Kevrekidis, A kernel-based method for data-driven Koopman spectral analysis, Journal of Computational Dynamics, vol.2, issue.2, pp.247-265, 2015.