Lyapunov Perception Contracts for Operating Design Domains

Yangge Li, Chenxi Ji, Jai Anchalia, Yixuan Jia, Benjamin C Yang, Daniel Zhuang, Sayan Mitra
Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, PMLR 283:1053-1065, 2025.

Abstract

There are two barriers to assessing the reliability of visual control systems that use machine learning (ML) models for perception and state estimation. First, the reasoning has to include the image rendering process, which is affected by environmental factors such as lighting and weather in complex ways. Second, we lack meaningful specifications for ML models like deep neural networks (DNNs). In this paper, we introduce Lyapunov Perception Contracts (LPC) as a method to address these challenges. We show how these contracts can be used as specifications for DNN-based state estimators, which assure closed-loop stability. We propose a method for synthesizing LPC from data and the models for the controller and plant dynamics. We also show how LPCs can be used to find operating design domains for visual controllers that operate in finitely parameterized environments. We illustrate applications of this method in a visual automated landing system using both data from simulations and GoogleEarth.

Cite this Paper

BibTeX
@InProceedings{pmlr-v283-li25c, title = {Lyapunov Perception Contracts for Operating Design Domains}, author = {Li, Yangge and Ji, Chenxi and Anchalia, Jai and Jia, Yixuan and Yang, Benjamin C and Zhuang, Daniel and Mitra, Sayan}, booktitle = {Proceedings of the 7th Annual Learning for Dynamics \& Control Conference}, pages = {1053--1065}, year = {2025}, editor = {Ozay, Necmiye and Balzano, Laura and Panagou, Dimitra and Abate, Alessandro}, volume = {283}, series = {Proceedings of Machine Learning Research}, month = {04--06 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v283/main/assets/li25c/li25c.pdf}, url = {https://proceedings.mlr.press/v283/li25c.html}, abstract = {There are two barriers to assessing the reliability of visual control systems that use machine learning (ML) models for perception and state estimation. First, the reasoning has to include the image rendering process, which is affected by environmental factors such as lighting and weather in complex ways. Second, we lack meaningful specifications for ML models like deep neural networks (DNNs). In this paper, we introduce Lyapunov Perception Contracts (LPC) as a method to address these challenges. We show how these contracts can be used as specifications for DNN-based state estimators, which assure closed-loop stability. We propose a method for synthesizing LPC from data and the models for the controller and plant dynamics. We also show how LPCs can be used to find operating design domains for visual controllers that operate in finitely parameterized environments. We illustrate applications of this method in a visual automated landing system using both data from simulations and GoogleEarth.} }
Endnote
%0 Conference Paper %T Lyapunov Perception Contracts for Operating Design Domains %A Yangge Li %A Chenxi Ji %A Jai Anchalia %A Yixuan Jia %A Benjamin C Yang %A Daniel Zhuang %A Sayan Mitra %B Proceedings of the 7th Annual Learning for Dynamics \& Control Conference %C Proceedings of Machine Learning Research %D 2025 %E Necmiye Ozay %E Laura Balzano %E Dimitra Panagou %E Alessandro Abate %F pmlr-v283-li25c %I PMLR %P 1053--1065 %U https://proceedings.mlr.press/v283/li25c.html %V 283 %X There are two barriers to assessing the reliability of visual control systems that use machine learning (ML) models for perception and state estimation. First, the reasoning has to include the image rendering process, which is affected by environmental factors such as lighting and weather in complex ways. Second, we lack meaningful specifications for ML models like deep neural networks (DNNs). In this paper, we introduce Lyapunov Perception Contracts (LPC) as a method to address these challenges. We show how these contracts can be used as specifications for DNN-based state estimators, which assure closed-loop stability. We propose a method for synthesizing LPC from data and the models for the controller and plant dynamics. We also show how LPCs can be used to find operating design domains for visual controllers that operate in finitely parameterized environments. We illustrate applications of this method in a visual automated landing system using both data from simulations and GoogleEarth.
APA
Li, Y., Ji, C., Anchalia, J., Jia, Y., Yang, B.C., Zhuang, D. & Mitra, S.. (2025). Lyapunov Perception Contracts for Operating Design Domains. Proceedings of the 7th Annual Learning for Dynamics \& Control Conference, in Proceedings of Machine Learning Research 283:1053-1065 Available from https://proceedings.mlr.press/v283/li25c.html.

Related Material