The DOI matches its Crossref record; 79 of the 81 references it cites were found in a registry or an index.
Finite Time Lyapunov Exponent Analysis of Model Predictive Control and Reinforcement Learning
Open accessAbstract
Finite-time Lyapunov exponents (FTLEs) provide a powerful approach to compute time-varying analogs of invariant manifolds in unsteady fluid flow fields. These manifolds are useful to visualize the transport mechanisms of passive tracers advecting with the flow. However, many vehicles and mobile sensors are not passive, but are instead actuated according to some intelligent trajectory planning or control law; for example, model predictive control and reinforcement learning are often used to design energy-efficient trajectories in a dynamically changing background flow. In this work, we investigate the use of FTLE on such controlled agents to gain insight into optimal transport routes for navigation in known unsteady flows. We find that these controlled FTLE (cFTLE) coherent structures separate the flow field into different regions with similar costs of transport to the goal location. These separatrices are functions of the planning algorithm’s hyper-parameters, such as the optimization time horizon and the cost of actuation. Computing the invariant sets and manifolds of active agent dynamics in dynamic flow fields is useful in the context of robust motion control, hyperparameter tuning, and determining safe and collision-free trajectories for autonomous systems. Moreover, these cFTLE structures provide insight into effective deployment locations for mobile agents with actuation and energy constraints to traverse the ocean or atmosphere.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225
Continuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782 · cited 1×
“In this study, we use the deep deterministic policy gradient (DDPG) method [76] available in the stable baselines package [71] to demonstrate the use of cFTLE analysis on reinforcement learning policies.”
MethodModel predictive control: Theory and practice—A survey
García, C. E., Prett, D. M., & Morari, M. (1989) · Automatica · doi:10.1016/0005-1098(89)90002-2 · Cited by 5,284 · cited 1×
“Among the existing methods, MPC [47], [48] and reinforcement learning [49], [50] are among the most useful paradigms in modern control [51], and analyzing these control laws and policies with FTLE be the focus of this paper.”
MethodCasADi: a software framework for nonlinear optimization and optimal control
Andersson, J. A. E., Gillis, J., Horn, G., Rawlings, J. B., & Diehl, M. (2019) · Mathematical Programming Computation · doi:10.1007/s12532-018-0139-4 · Cited by 3,868 · cited 1×
“To solve the resulting optimization problems of MPC, we use the CasADi [69] and MPCTools [70] packages, which use an interior point filter-line search algorithm (IPOPT).”
MethodSastry, S. (1999) · Interdisciplinary Applied Mathematics · doi:10.1007/978-1-4757-3108-8 · Cited by 1,764 · cited 1×
“When using optimal control methods, the policy can often make the controlled system a non-smooth dynamical system [75].”
MethodOptimal Control and Estimation
Stengel, R. F. (1994) · Cited by 1,617
Shadden, S. C., Lekien, F., & Marsden, J. E. (2005) · Physica D: Nonlinear Phenomena · doi:10.1016/j.physd.2005.10.007 · Cited by 1,326 · cited 4×
“The finite-time Lyapunov exponent quantifies this stretching over a fixed, finite-time horizon, resulting in a scalar field over a domain of interest highlighting the most sensitive regions to perturbations in the initial conditions [9], [10], [11], [12], [13].”
BackgroundMethodInfluentialLagrangian Coherent Structures
Haller, G. (2015) · Annual Review of Fluid Mechanics · doi:10.1146/annurev-fluid-010313-141322 · Cited by 1,037
Wynn, R. B., Huvenne, V. A. I., Le Bas, T. P., Murton, B. J., Connelly, D. P., Bett, B. J., Ruhl, H. A., Morris, K. J., Peakall, J., Parsons, D. R., et al. (2014) · Marine Geology · doi:10.1016/j.margeo.2014.03.012 · Cited by 1,003
Stable-Baselines3: Reliable Reinforcement Learning Implementations
Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., & Dormann, N. (2021) · elib (German Aerospace Center) · Cited by 1,000
Research works printed but not linked: 4
- bhatta, 2005, Coordination of an underwater glider fleet for adaptive ocean sampling, Proc Int Workshop Underwater Robot Int Adv Robot Programmed (IARP), 61
- risbeck, 2015, Mpctools Nonlinear model predictive control tools for casadi (python interface)
- speich, 1994, Interannual variability of the mid-latitude oceans: A new source of climate variability, Sist Terra, 3, 459
- 10.7551/mitpress/9780262042383.003.0012 · doi:10.7551/mitpress/9780262042383.003.0012
Cited by
Sensing flow gradients is necessary for learning autonomous underwater navigation
Jiao, Y., Hang, H., Merel, J., & Kanso, E. (2025) · Nature Communications · doi:10.1038/s41467-025-58125-6 · Cited by 23
Optimal tracking strategies in a turbulent flow
Calascibetta, C., Biferale, L., Borra, F., Celani, A., & Cencini, M. (2023) · Communications Physics · doi:10.1038/s42005-023-01366-y · Cited by 21
Uncertainties in the finite-time Lyapunov exponent in an ocean ensemble prediction model
Matuszak, M., Röhrs, J., Isachsen, P. E., & Idžanović, M. (2025) · Ocean science · doi:10.5194/os-21-401-2025 · Cited by 6
Super-resolution reconstruction of turbulent flows from a single Lagrangian trajectory
Wu, H.-L., Xu, A., & Xi, H.-D. (2026) · Journal of Fluid Mechanics · doi:10.1017/jfm.2025.11033 · Cited by 5
Surfing vortex rings for energy-efficient propulsion
Gunnarson, P. J., & Dabiri, J. O. (2025) · PNAS Nexus · doi:10.1093/pnasnexus/pgaf031 · Cited by 6
“Recent algorithmic approaches have involved data-driven techniques such as reinforcement learning, in which onboard flow measurements provided sufficient information to navigate through a variety of unsteady canonical and oceanic flow environments (e.g. (13 – 18)).”
Metadata
- Authors
- Krishna, K., Brunton, S. L., & Song, Z.
- Affiliations
- University of Washington (US)
- University of Hawaiʻi at Mānoa (US)
- Venue
- IEEE Access
- Published
- 2023
- Volume
- 11
- Pages
- 118916-118930
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4387831842
- Cited by
- 12
- References
- 81
- Citations by year
- 2026: 4 · 2025: 5 · 2024: 1 · 2023: 2
- FWCI
- 4.88
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- IEEE Access (publishedVersion, cc-by-nc-nd)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Funders
- National Science Foundation for the project ‘AI Institute in Dynamic Systems’ (2112085)
- U.S. Air Force Office of Scientific Research (FA9550-21-1-0178)
- Topics
- Physical Sciences › Mathematics › Mathematical Physics › Mathematical Dynamics and Fractals
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Quantum chaos and dynamical systems
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Model Reduction and Neural Networks
- Keywords
- finite-time Lyapunov exponents, model predictive control, reinforcement learning, coherent structures, invariant manifolds, unsteady flow, active agents, transportation costs, trajectory planning, autonomous navigation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Finite Time Lyapunov Exponent Analysis of Model Predictive Control and Reinforcement Learning. https://app.cochat.ai/papers/10.1109/access.2023.3326424
- The paper
- Krishna, K., Brunton, S. L., & Song, Z. (2023). Finite Time Lyapunov Exponent Analysis of Model Predictive Control and Reinforcement Learning. IEEE Access. https://doi.org/10.1109/access.2023.3326424
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.