The DOI matches its Crossref record; 69 of the 69 references it cites were found in a registry or an index.
Safe Control With Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction Methods for Robotics and Control
Abstract
Learning-enabled control systems have demonstrated impressive empirical performance on challenging control problems in robotics, but this performance comes at the cost of reduced transparency and lack of guarantees on the safety or stability of the learned controllers. In recent years, new techniques have emerged to provide these guarantees by learning certificates alongside control policies—these certificates provide concise data-driven proofs that guarantee the safety and stability of the learned control system. These methods not only allow the user to verify the safety of a learned controller but also provide supervision during training, allowing safety and stability requirements to influence the training process itself. In this article, we provide a comprehensive survey of this rapidly developing field of certificate learning. We hope that this article will serve as an accessible introduction to the theory and practice of certificate learning, both to those who wish to apply these tools to practical robotics problems and to those who wish to dive more deeply into the theory of learning for control.
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
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2020) · Nature Methods · doi:10.1038/s41592-019-0686-2 · Cited by 38,430
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2019) · Apollo - University of Cambridge Repository · doi:10.17863/cam.64134 · Cited by 10,460
Towards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602
On Assessing ML Model Robustness: A Methodological Framework (Academic Track)
Awadid, A., & Robert, B. (2025) · OASIcs : OpenAccess Series in Informatics · doi:10.4230/oasics.saia.2024.1 · Cited by 4,702
On the approximate realization of continuous mappings by neural networks
Funahashi, K.-I. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90003-8 · Cited by 4,206 · cited 1×
“By increasing the size of these networks, this representation can approximate any continuous function [45], [46], alleviating limitations due to the choice of function space.”
BackgroundCasADi: 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
Control Barrier Function Based Quadratic Programs for Safety Critical Systems
Ames, A. D., Xu, X., Grizzle, J. W., & Tabuada, P. (2017) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2016.2638961 · Cited by 2,512
Contraction Analysis of Nonlinear SystemsPreprint
Slotine, J.-J. E. (1999) · Cited by 1,532
Satisfiability Modulo Theories
Barrett, C., & Tinelli, C. (2018) · Handbook of Model Checking · doi:10.1007/978-3-319-10575-8_11 · Cited by 1,122
Robust Nonlinear Control Design
Freeman, R. A., & Kokotović, P. (1996) · Birkhäuser Boston eBooks · doi:10.1007/978-0-8176-4759-9 · Cited by 955
Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning
Brunke, L., Greeff, M., Hall, A. W., Yuan, Z., Zhou, S., Panerati, J., & Schoellig, A. P. (2022) · Annual Review of Control, Robotics, and Autonomous Systems · doi:10.1146/annurev-control-042920-020211 · Cited by 769
Cheng, R., Orosz, G., Murray, R. M., & Burdick, J. W. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33013387 · Cited by 611 · cited 1×
“The first class of methods use an a priori given certificate to constrain the actions that the RL agent can take [33], [34], [35], possibly with some learning of model uncertainty as the controller explores [33], [34].”
MethodHamilton-Jacobi reachability: A brief overview and recent advances
Bansal, S., Chen, M., Herbert, S., & Tomlin, C. J. (2017) · 2017 IEEE 56th Annual Conference on Decision and Control (CDC) · doi:10.1109/cdc.2017.8263977 · Cited by 471
CommonRoad: Composable benchmarks for motion planning on roads
Althoff, M., Koschi, M., & Manzinger, S. (2017) · 2017 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2017.7995802 · Cited by 443 · cited 3×
“We use the single-track car model from the CommonRoad benchmarks [89].”
MethodInfluentialRapidly Exponentially Stabilizing Control Lyapunov Functions and Hybrid Zero Dynamics
Ames, A. D., Galloway, K., Sreenath, K., & Grizzle, J. W. (2014) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2014.2299335 · Cited by 440
dReal: An SMT Solver for Nonlinear Theories over the Reals
Gao, S., Kong, S., & Clarke, E. M. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-38574-2_14 · Cited by 413
Self-citationApproximation and estimation bounds for artificial neural networks
Barron, A. R. (1994) · Machine Learning · doi:10.1007/bf00993164 · Cited by 399
Algorithms for Verifying Deep Neural Networks
Liu, C., Arnon, T., Lazarus, C., Strong, C., Barrett, C., & Kochenderfer, M. J. (2021) · Foundations and Trends in Optimization · doi:10.1561/2400000035 · Cited by 333
Agrawal, A., & Sreenath, K. (2017) · Robotics: Science and Systems XIII · doi:10.15607/rss.2017.xiii.073 · Cited by 296
Lyapunov-based Safe Policy Optimization for Continuous ControlPreprint
Chow, Y., Nachum, O., Faust, A., Duéñez‐Guzmán, E. A., & Ghavamzadeh, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.10031 · Cited by 287
Neural Lander: Stable Drone Landing Control Using Learned Dynamics
Shi, G., Shi, X., O'Connell, M., Yu, R., Azizzadenesheli, K., Anandkumar, A., Yue, Y., & Chung, S.-J. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8794351 · Cited by 281
Review on computational methods for Lyapunov functions
Giesl, P., & Hafstein, S. (2015) · Discrete and Continuous Dynamical Systems - B · doi:10.3934/dcdsb.2015.20.2291 · Cited by 260
Neural Lyapunov ControlPreprint
Chang, Y.-C., Roohi, N., & Gao, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.00611 · Cited by 259
Self-citationLearning for Safety-Critical Control with Control Barrier FunctionsPreprint
Taylor, A. J., Singletary, A., Yue, Y., & Ames, A. D. (2019) · arXiv (Cornell University) · doi:10.13140/rg.2.2.21587.60962 · Cited by 254
Control Contraction Metrics: Convex and Intrinsic Criteria for Nonlinear Feedback Design
Manchester, I. R., & Slotine, J.-J. E. (2017) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2017.2668380 · Cited by 228
Choi, J., Castañeda, F., Tomlin, C., & Sreenath, K. (2020) · Robotics: Science and Systems XVI · doi:10.15607/rss.2020.xvi.088 · Cited by 194
Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach
Srinivasan, M., Dabholkar, A., Coogan, S., & Vela, P. A. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341190 · Cited by 189
Learning Control Barrier Functions from Expert Demonstrations
Robey, A., Hu, H., Lindemann, L., Zhang, H., Dimarogonas, D. V., Tu, S., & Matni, N. (2020) · 2020 59th IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc42340.2020.9303785 · Cited by 172
Formal Synthesis of Lyapunov Neural Networks
Abate, A., Ahmed, D., Giacobbe, M., & Peruffo, A. (2020) · IEEE Control Systems Letters · doi:10.1109/lcsys.2020.3005328 · Cited by 149
Simulation-guided lyapunov analysis for hybrid dynamical systems
Kapinski, J. P., Deshmukh, J. V., Sankaranarayanan, S., & Aréchiga, N. (2014) · International Conference on Hybrid Systems: computation and control · doi:10.1145/2562059.2562139 · Cited by 147
Contraction theory for nonlinear stability analysis and learning-based control: A tutorial overview
Tsukamoto, H., Chung, S.-J., & Slotine, J.-J. E. (2021) · Annual Reviews in Control · doi:10.1016/j.arcontrol.2021.10.001 · Cited by 145
Control design along trajectories with sums of squares programming
Majumdar, A., Ahmadi, A. A., & Tedrake, R. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631149 · Cited by 140
Learning Safe Multi-Agent Control with Decentralized Neural Barrier CertificatesPreprint
Qin, Z., Zhang, K., Chen, Y., Chen, J., & Fan, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05436 · Cited by 136
Self-citationRobust Control Barrier–Value Functions for Safety-Critical Control
Choi, J. J., Lee, D., Sreenath, K., Tomlin, C. J., & Herbert, S. (2021) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc45484.2021.9683085 · Cited by 131
Learning Stability Certificates from DataPreprint
Boffi, N. M., Tu, S., Matni, N., Slotine, J.-J. E., & Sindhwani, V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.05952 · Cited by 128
Learning Stable Deep Dynamics ModelsPreprint
Manek, G., & Kolter, J. Z. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.06116 · Cited by 125
DryVR: Data-Driven Verification and Compositional Reasoning for Automotive Systems
Fan, C., Qi, B., Mitra, S., & Viswanathan, M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-63387-9_22 · Cited by 120
Self-citationDeepReach: A Deep Learning Approach to High-Dimensional Reachability
Bansal, S., & Tomlin, C. J. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9561949 · Cited by 116
Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems
Taylor, A. J., Dorobantu, V. D., Le, H., Yue, Y., & Ames, A. D. (2019) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros40897.2019.8967820 · Cited by 97
Permissive Barrier Certificates for Safe Stabilization Using Sum-of-squares
Wang, L., Han, D., & Egerstedt, M. (2018) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc.2018.8431617 · Cited by 97
Safety-Critical Control With Input Delay in Dynamic Environment
Molnar, T. G., Kiss, A. K., Ames, A. D., & Orosz, G. (2023) · IEEE Transactions on Control Systems Technology · doi:10.1109/tcst.2022.3227451 · Cited by 83 · cited 5×
“All of the certificates discussed above allow the control engineer to prove that her controller design is sound (or, in the case of CLFs and CBFs, derive a sound controller directly from the Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
BackgroundInfluentialSafe Nonlinear Control Using Robust Neural Lyapunov-Barrier FunctionsPreprint
Dawson, C., Qin, Z., Gao, S., & Fan, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.06697 · Cited by 81
Self-citationLearning stabilizable nonlinear dynamics with contraction-based regularization
Singh, S., Richards, S. M., Sindhwani, V., Slotine, J.-J. E., & Pavone, M. (2020) · The International Journal of Robotics Research · doi:10.1177/0278364920949931 · Cited by 76
Abate, A., Ahmed, D., Edwards, A., Giacobbe, M., & Peruffo, A. (2021) · International Conference on Hybrid Systems: computation and control · doi:10.1145/3447928.3456646 · Cited by 73
Verification of Image-Based Neural Network Controllers Using Generative Models
Katz, S. M., Corso, A., Strong, C. A., & Kochenderfer, M. J. (2022) · Journal of Aerospace Information Systems · doi:10.2514/1.i011071 · Cited by 71
Some applications of polynomial optimization in operations research and real-time decision making
Ahmadi, A. A., & Majumdar, A. (2015) · Optimization Letters · doi:10.1007/s11590-015-0894-3 · Cited by 70
Neural Contraction Metrics for Robust Estimation and Control: A Convex Optimization Approach
Tsukamoto, H., & Chung, S. (2020) · IEEE Control Systems Letters · doi:10.1109/lcsys.2020.3001646 · Cited by 67
Synthesizing barrier certificates using neural networks
Zhao, H., Zeng, X. L., Chen, T., & Liu, Z. (2020) · International Conference on Hybrid Systems: computation and control · doi:10.1145/3365365.3382222 · Cited by 66
Learning Certified Control using Contraction MetricPreprint
Sun, D., Jha, S., & Fan, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.12569 · Cited by 66
Self-citationAutomated and Sound Synthesis of Lyapunov Functions with SMT Solvers
Ahmed, D., Peruffo, A., & Abate, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-45190-5_6 · Cited by 62
Stabilizing Neural Control Using Self-Learned Almost Lyapunov Critics
Chang, Y.-C., & Gao, S. (2021) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48506.2021.9560886 · Cited by 49
Self-citationTemporal Logic Guided Safe Reinforcement Learning Using Control Barrier FunctionsPreprint
Li, X., & Belta, C. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.09885 · Cited by 48
Castañeda, F., Choi, J. J., Zhang, B., Tomlin, C. J., & Sreenath, K. (2021) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc50511.2021.9483420 · Cited by 48
Lyapunov-Net: A Deep Neural Network Architecture for Lyapunov Function Approximation
Gaby, N., Zhang, F., & Ye, X. (2022) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc51059.2022.9993006 · Cited by 44
Compositional Learning and Verification of Neural Network Controllers
Ivanov, R., Jothimurugan, K., Hsu, S., Vaidya, S., Alur, R., & Bastani, O. (2021) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3477023 · Cited by 43
Automated-Sampling-Based Stability Verification and DOA Estimation for Nonlinear Systems
Bobiti, R., & Lazar, M. (2018) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2018.2797196 · Cited by 37
Learning Hybrid Control Barrier Functions from DataPreprint
Lindemann, L., Hu, H., Robey, A., Zhang, H., Dimarogonas, D. V., Tu, S., & Matni, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.04112 · Cited by 37
Towards Robust Data-Driven Control Synthesis for Nonlinear Systems with Actuation Uncertainty
Taylor, A. J., Dorobantu, V. D., Dean, S., Recht, B., Yue, Y., & Ames, A. D. (2021) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc45484.2021.9683511 · Cited by 36
Learning lyapunov functions for hybrid systems
Chen, S., Fazlyab, M., Morari, M., Pappas, G. J., & Preciado, V. M. (2021) · International Conference on Hybrid Systems: computation and control · doi:10.1145/3447928.3456644 · Cited by 35
Neural Stochastic Contraction Metrics for Learning-Based Control and Estimation
Tsukamoto, H., Chung, S., & Slotine, J.-J. E. (2020) · IEEE Control Systems Letters · doi:10.1109/lcsys.2020.3046529 · Cited by 34
Sablas: Learning Safe Control for Black-Box Dynamical Systems
Qin, Z., Sun, D., & Fan, C. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3142743 · Cited by 32
Self-citationNeural Stochastic Contraction Metrics for Learning-based Control and Estimation
Tsukamoto, H., Chung, S., & Slotine, J.-J. E. (2021) · CaltechAUTHORS (California Institute of Technology) · Cited by 30
Discrete-time control design with positive semi-definite Lyapunov functions
Grizzle, J. W., & Kang, J. (2001) · Systems & Control Letters · doi:10.1016/s0167-6911(01)00110-4 · Cited by 27
BarrierNet: A Safety-Guaranteed Layer for Neural NetworksPreprint
Xiao, W., Hasani, R., Li, X., & Rus, D. L. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.11277 · Cited by 22
Sparse Semidefinite Programs with Near-Linear Time Complexity
Zhang, R. Y., & Lavaei, J. (2018) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc.2018.8619478 · Cited by 21
Communication Topology Co-Design in Graph Recurrent Neural Network based Distributed Control
Yang, F., & Matni, N. (2021) · Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes · doi:10.1109/cdc45484.2021.9683779 · Cited by 16
Reactive and Safe Road User Simulations using Neural Barrier CertificatesPreprint
Meng, Y., Qin, Z., & Fan, C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.06689 · Cited by 10
Self-citationLearning Min-norm Stabilizing Control Laws for Systems with Unknown Dynamics
Westenbroek, T., Castaneda, F., Agrawal, A., Sastry, S., & Sreenath, K. (2020) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc42340.2020.9304118 · Cited by 7
Cited by
Neural Operators for Bypassing Gain and Control Computations in PDE Backstepping
Bhan, L., Shi, Y., & Krstic, M. (2024) · IEEE Transactions on Automatic Control · doi:10.1109/tac.2023.3347499 · Cited by 58
Metadata
- Authors
- Dawson, C., Gao, S., & Fan, C.
- Venue
- IEEE Transactions on Robotics
- Published
- 2023-06
- Volume
- 39
- Issue
- 3
- Pages
- 1749-1767
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W4315606134
- Cited by
- 269
- References
- 69
- FWCI
- 23.63
- Type
- journal article
- Language
- en
- Open access
- closed
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
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.