Year: 2026

1 paper accepted to L4DC

by

Our paper on data-driven acceleration of Model Predictive Control (MPC) [1] has been accepted to the 8th Annual Learning for Dynamics and Control Conference. Congrats to Agustin and Shijie!

[1] A. Castellano, S. Pan, and E. Mallada, “Data-driven Acceleration of MPC with Guarantees,” in Proceedings of The 8th Annual Learning for Dynamics and Control Conference, 2026.
[Bibtex] [Abstract] [Download PDF]

Model Predictive Control (MPC) is a powerful framework for optimal control but can be too slow for low-latency applications. We present a data-driven framework to accelerate MPC by replacing online optimization with a nonparametric policy constructed from offline MPC solutions. Our policy is greedy with respect to a constructed upper bound on the optimal cost-to-go, and can be implemented as a nonparametric lookup rule that is orders of magnitude faster than solving MPC online. Our analysis shows that under sufficient coverage condition of the offline data, the policy is recursively feasible and admits provable, bounded optimality gap. These conditions establish an explicit trade-off between the amount of data collected and the tightness of the bounds. Our experiments show that this policy is between $100$ and $1000$ times faster than standard MPC, with only a modest hit to optimality, showing potential for real-time control tasks.

@inproceedings{cpm2026l4dc,
  abstract = {Model Predictive Control (MPC) is a powerful framework for optimal control but can be too slow for low-latency applications. We present a data-driven framework to accelerate MPC by replacing online optimization with a nonparametric policy constructed from offline MPC solutions. Our policy is greedy with respect to a constructed upper bound on the optimal cost-to-go, and can be implemented as a nonparametric lookup rule that is orders of magnitude faster than solving MPC online. Our analysis shows that under sufficient coverage condition of the offline data, the policy is recursively feasible and admits provable, bounded optimality gap. These conditions establish an explicit trade-off between the amount of data collected and the tightness of the bounds. Our experiments show that this policy is between $100$ and $1000$ times faster than standard MPC, with only a modest hit to optimality, showing  potential for real-time control tasks.},
  author = {Castellano, Agustin and Pan, Shijie and Mallada, Enrique},
  booktitle = {Proceedings of The 8th Annual Learning for Dynamics and Control Conference},
  grants = {Global-Centers-2330450; DOE-ASCR-826565},
  month = {6},
  organization = {PMLR},
  pubstate = {accepted},
  record = {accepted Mar. 2026, submitted Nov. 2025},
  title = {Data-driven Acceleration of MPC with Guarantees},
  url = {https://mallada.ece.jhu.edu/pubs/2026-L4DC-CPM.pdf},
  year = {2026}
}

2 papers accepted to ACC

by

Our papers on safety-critical control via recurrent tracking functions [1] and on data-driven practical stabilization via chain policies [2] have been accepted to the American Control Conference. Congrats Jixian and Roy!

[1] J. Liu and E. Mallada, “Safety-Critical Control via Recurrent Tracking Functions,” in American Control Conference (ACC), 2026, pp. 1-7.
[Bibtex] [Abstract] [Download PDF]

This paper addresses the challenge of synthesizing safety-critical controllers for high-order nonlinear systems, where constructing valid Control Barrier Functions (CBFs) remains computationally intractable. Leveraging layered control, we design CBFs in reduced-order models (RoMs) while regulating full-order models’ (FoMs) dynamics at the same time. Traditional Lyapunov tracking functions are required to decrease monotonically, but systematic synthesis methods for such functions exist only for fully-actuated systems. To overcome this limitation, we introduce Recurrent Tracking Functions (RTFs), which replace the monotonic decay requirement with a weaker finite-time recurrence condition. This relaxation permits transient deviations of tracking errors while ensuring safety. By augmenting CBFs for RoMs with RTFs, we construct recurrent CBFs (RCBFs) whose zero-superlevel set is control $τ$-recurrent, and guarantee safety for all initial states in such a set when RTFs are satisfied. We establish theoretical safety guarantees and validate the approach through numerical experiments, demonstrating RTFs’ effectiveness and the safety of FoMs.

@inproceedings{lm2026acc,
  abstract = {This paper addresses the challenge of synthesizing safety-critical controllers for high-order nonlinear systems, where constructing valid Control Barrier Functions (CBFs) remains computationally intractable. Leveraging layered control, we design CBFs in reduced-order models (RoMs) while regulating full-order models' (FoMs) dynamics at the same time. Traditional Lyapunov tracking functions are required to decrease monotonically, but systematic synthesis methods for such functions exist only for fully-actuated systems. To overcome this limitation, we introduce Recurrent Tracking Functions (RTFs), which replace the monotonic decay requirement with a weaker finite-time recurrence condition. This relaxation permits transient deviations of tracking errors while ensuring safety. By augmenting CBFs for RoMs with RTFs, we construct recurrent CBFs (RCBFs) whose zero-superlevel set is control $τ$-recurrent, and guarantee safety for all initial states in such a set when RTFs are satisfied. We establish theoretical safety guarantees and validate the approach through numerical experiments, demonstrating RTFs' effectiveness and the safety of FoMs.},
  author = {Liu, Jixian and Mallada, Enrique},
  bdsk-url-3 = {https://doi.org/10.23919/ACC55779.2023.10156212},
  booktitle = {American Control Conference (ACC)},
  grants = {Global-Centers-2330450; DOE-ASCR-826565},
  month = {5},
  pages = {1-7},
  pubstate = {accepted},
  record = {accepted Feb. 2026, submitted Sep. 2025},
  title = {Safety-Critical Control via Recurrent Tracking Functions},
  url = {https://mallada.ece.jhu.edu/pubs/2026-ACC-LM.pdf},
  year = {2026}
}
[2] R. Siegelmann and E. Mallada, “Data-driven Practical Stabilization of Nonlinear Systems via Chain Policies: Sample Complexity and Incremental Learning,” in American Control Conference (ACC), 2026, pp. 1-8.
[Bibtex] [Abstract] [Download PDF]

We propose a method for data-driven practical stabilization of nonlinear systems with provable guarantees, based on the concept of \emphNonparametric Chain Policies (NCPs). The approach employs a normalized nearest-neighbor rule to assign, at each state, a finite-duration control signal derived from stored data, after which the process repeats. Unlike recent works that model the system as linear, polynomial, or polynomial fraction, we only assume the system to be locally Lipschitz. Our analysis build son the framework of Recurrent Lyapunov Functions (RLFs), which enable data-driven certification of (practical) stability using standard norm functions instead of requiring the explicit construction of a classical Lyapunov function. To extend this framework, we introduce the concept of Recurrent Control Lyapunov Functions (R-CLFs), which can certify the existence of an NCP that practically stabilizes an arbitrarily small $c$-neighborhood of an equilibrium point. We also provide an explicit sample complexity guarantee of $\mathcalO\!łeft((3/h̊o)^d łog(R/c)\g̊ht)$ number of trajectories—where $R$ is the domain radius, $d$ the state dimension, and $\r$̊ a system-dependent constant. The proposed Chain Policies are nonparametric, thus allowing new verified data to be readily incorporated into the policy to either improve convergence rate or enlarge the certified region. Numerical experiments illustrate and validate these properties.

@inproceedings{sm2026acc,
  abstract = {We propose a method for data-driven practical stabilization of nonlinear systems with provable guarantees, based on the concept of \emphNonparametric Chain Policies (NCPs). The approach employs a normalized nearest-neighbor rule to assign, at each state, a finite-duration control signal derived from stored data, after which the process repeats. 
Unlike recent works that model the system as linear, polynomial, or polynomial fraction, we only assume the system to be locally Lipschitz.
Our analysis build son the framework of Recurrent Lyapunov Functions (RLFs), which enable data-driven certification of (practical) stability using standard norm functions instead of requiring the explicit construction of a classical Lyapunov function. To extend this framework, we introduce the concept of Recurrent Control Lyapunov Functions (R-CLFs), which can certify the existence of an NCP that practically stabilizes an arbitrarily small $c$-neighborhood of an equilibrium point. 
We also provide an explicit sample complexity guarantee of $\mathcalO\!łeft((3/h̊o)^d łog(R/c)\g̊ht)$ number of trajectories---where $R$ is the domain radius, $d$ the state dimension, and $\r$̊ a system-dependent constant. The proposed Chain Policies are nonparametric, thus allowing new verified data to be readily incorporated into the policy to either improve convergence rate or enlarge the certified region. Numerical experiments illustrate and validate these properties.},
  author = {Siegelmann, Roy and Mallada, Enrique},
  bdsk-url-3 = {https://doi.org/10.23919/ACC55779.2023.10156212},
  booktitle = {American Control Conference (ACC)},
  grants = {Global-Centers-2330450; DOE-ASCR-826565},
  month = {5},
  pages = {1-8},
  pubstate = {accepted},
  record = {accepted Feb. 2026, submitted Sep. 2025},
  title = {Data-driven Practical Stabilization of Nonlinear Systems via Chain Policies: Sample Complexity and Incremental Learning},
  url = {https://mallada.ece.jhu.edu/pubs/2026-ACC-SgM.pdf},
  year = {2026}
}

1 paper published in NAHS

by

Our paper on recurrence entropy of nonlinear control systems [1] has been published in Nonlinear Analysis: Hybrid Systems. The paper shows that making a set recurrent, in the sense that trajectories starting in the set must return to it, is provably less complex than making it invariant, and characterizes the minimum data rates and finite control alphabets needed to achieve it.

[1] [doi] H. Sibai and E. Mallada, “Recurrence of Nonlinear Control Systems: Entropy, Bit Rates, and Finite Alphabets,” Nonlinear Analysis: Hybrid Systems, vol. 59, iss. 101649, pp. 1-16, 2026.
[Bibtex] [Abstract] [Download PDF]

In this paper, we introduce the notion of recurrence entropy in the context of nonlinear control systems. A set is said to be ($τ$-)recurrent if every trajectory that starts in the set returns to it (within at most $τ$ units of time). The recurrence entropy of a control system quantifies the complexity of making a set $τ$-recurrent measured by the average rate of growth, as time increases, of the number of control signals required to achieve this goal. Our analysis reveals that, compared to invariance, recurrence is quantitatively less complex, meaning that the recurrence entropy of a set is no larger than, and often strictly smaller than, the invariance entropy. We provide upper and lower bounds on recurrence entropy and show that they converge to the bounds on invariance entropy as $τ$ decreases to zero. Further, our results show that recurrence entropy lower bounds the minimum data rate between the sensor and controller required for achieving recurrence. We present an algorithm according to which the sensor can send state estimates to the controller over a limited-bandwidth channel to achieve recurrence asymptotically at an exponential rate. Finally, we show that, under mild stricter conditions on the set and dynamics, the control signals that enforce the $τ$-recurrence of a set can be generated by a finite alphabet of control signals of durations of at most $τ$ units of time, which allows us to store them for quick online execution.

@article{sm2026nahs,
  abstract = {In this paper, we introduce the notion of recurrence entropy in the context of nonlinear control systems. A set is said to be ($τ$-)recurrent if every trajectory that starts in the set returns to it (within at most $τ$ units of time). The recurrence entropy of a control system quantifies the complexity of making a set $τ$-recurrent measured by the average rate of growth, as time increases, of the number of control signals required to achieve this goal. Our analysis reveals that, compared to invariance, recurrence is quantitatively less complex, meaning that the recurrence entropy of a set is no larger than, and often strictly smaller than, the invariance entropy. We provide upper and lower bounds on recurrence entropy and show that they converge to the bounds on invariance entropy as $τ$ decreases to zero. Further, our results show that recurrence entropy lower bounds the minimum data rate between the sensor and controller required for achieving recurrence. We present an algorithm according to which the sensor can send state estimates to the controller over a limited-bandwidth channel to achieve recurrence asymptotically at an exponential rate. Finally, we show that, under mild stricter conditions on the set and dynamics, the control signals that enforce the $τ$-recurrence of a set can be generated by a finite alphabet of control signals of durations of at most $τ$ units of time, which allows us to store them for quick online execution.},
  author = {Sibai, Hussein and Mallada, Enrique},
  doi = {https://doi.org/10.1016/j.nahs.2025.101649},
  grants = {CPS-2136324; Global-Centers-2330450; CAREER-1752362},
  journal = {Nonlinear Analysis: Hybrid Systems},
  month = {2},
  number = {101649},
  pages = {1-16},
  record = {published Feb 2026, online Oct 2025, accepted Oct 2025, submitted Feb 2025},
  title = {Recurrence of Nonlinear Control Systems: Entropy, Bit Rates, and Finite Alphabets},
  url = {https://mallada.ece.jhu.edu/pubs/2026-NAHS-SM.pdf},
  volume = {59},
  year = {2026}
}