首页/论文/1908.00697

arXiv 1908.006972019-08math.OCcs.SYeess.SY

Model-Free Stochastic Reachability Using Kernel Distribution Embeddings

Adam J. Thorpe, Meeko M. K. Oishi

发表信息：: in IEEE Control Systems Letters, vol. 4, no. 2, pp. 512-517, April 2020
DOI：: 10.1109/LCSYS.2019.2954102

英文摘要：

We present a solution to the terminal-hitting stochastic reach-avoid problem for a Markov control process. This solution takes advantage of a nonparametric representation of the stochastic kernel as a conditional distribution embedding within a reproducing kernel Hilbert space (RKHS). Because the disturbance is modeled as a data-driven stochastic process, this representation avoids intractable integrals in the dynamic recursion of the reach-avoid problem since the expectations can be calculated as an inner product within the RKHS. We demonstrate this approach on a high-dimensional chain of integrators and on Clohessy-Wiltshire-Hill dynamics.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

SReachTools Kernel Module: Data-Driven Stochastic Reachability Using Hilbert Space Embeddings of Distributions

We present algorithms for performing data-driven stochastic reachability as an addition to SReachTools, an open-source stochastic reachability toolbox. Our method leverages a class of machine learning techniques known as kernel embeddings of distributions to approximate the safety probabilities for a wide variety of stochastic reachability problems. By representing the probability distributions of the system state as elements in a reproducing kernel Hilbert space, we can learn the "best fit" distribution via a simple regularized least-squares problem, and then compute the stochastic reachabili…

2021-03-22cs.SYeess.SYmath.OC

State-Based Confidence Bounds for Data-Driven Stochastic Reachability Using Hilbert Space Embeddings

In this paper, we compute finite sample bounds for data-driven approximations of the solution to stochastic reachability problems. Our approach uses a nonparametric technique known as kernel distribution embeddings, and provides probabilistic assurances of safety for stochastic systems in a model-free manner. By implicitly embedding the stochastic kernel of a Markov control process in a reproducing kernel Hilbert space, we can approximate the safety probabilities for stochastic systems with arbitrary stochastic disturbances as simple matrix operations and inner products. We present finite samp…

2021-12-07cs.SYeess.SYmath.OC

SOCKS: A Stochastic Optimal Control and Reachability Toolbox Using Kernel Methods

University of New Mexico（新墨西哥大学）

We present SOCKS, a data-driven stochastic optimal control toolbox based in kernel methods. SOCKS is a collection of data-driven algorithms that compute approximate solutions to stochastic optimal control problems with arbitrary cost and constraint functions, including stochastic reachability, which seeks to determine the likelihood that a system will reach a desired target set while respecting a set of pre-defined safety constraints. Our approach relies upon a class of machine learning algorithms based in kernel methods, a nonparametric technique which can be used to represent probability dis…

2022-03-12cs.LGcs.SYeess.SY

Approximate Stochastic Reachability for High Dimensional Systems

We present a method to compute the stochastic reachability safety probabilities for high-dimensional stochastic dynamical systems. Our approach takes advantage of a nonparametric learning technique known as conditional distribution embeddings to model the stochastic kernel using a data-driven approach. By embedding the dynamics and uncertainty within a reproducing kernel Hilbert space, it becomes possible to compute the safety probabilities for stochastic reachability problems as simple matrix operations and inner products. We employ a convergent approximation technique, random Fourier feature…

2020-10-15cs.SYeess.SYmath.OC

Verification of safety critical control policies using kernel methods

University of Oxford（牛津大学）；Paderborn University（帕德博恩大学）

Hamilton-Jacobi reachability methods for safety-critical control have been well studied, but the safety guarantees derived rely on the accuracy of the numerical computation. Thus, it is crucial to understand and account for any inaccuracies that occur due to uncertainty in the underlying dynamics and environment as well as the induced numerical errors. To this end, we propose a framework for modeling the error of the value function inherent in Hamilton-Jacobi reachability using a Gaussian process. The derived safety controller can be used in conjuncture with arbitrary controllers to provide a …

2022-03-23cs.LGcs.SYeess.SY

Kernel Center Adaptation in the Reproducing Kernel Hilbert Space Embedding Method

The performance of adaptive estimators that employ embedding in reproducing kernel Hilbert spaces (RKHS) depends on the choice of the location of basis kernel centers. Parameter convergence and error approximation rates depend on where and how the kernel centers are distributed in the state-space. In this paper, we develop the theory that relates parameter convergence and approximation rates to the position of kernel centers. We develop criteria for choosing kernel centers in a specific class of systems - ones in which the state trajectory regularly visits the neighborhood of the positive limi…

2020-09-07cs.SYeess.SYmath.OC

更多相关论文收起更多论文

Approximations of the Reproducing Kernel Hilbert Space (RKHS) Embedding Method over Manifolds

The reproducing kernel Hilbert space (RKHS) embedding method is a recently introduced estimation approach that seeks to identify the unknown or uncertain function in the governing equations of a nonlinear set of ordinary differential equations (ODEs). While the original state estimate evolves in Euclidean space, the function estimate is constructed in an infinite-dimensional RKHS that must be approximated in practice. When a finite-dimensional approximation is constructed using a basis defined in terms of shifted kernel functions centered at the observations along a trajectory, the RKHS embedd…

2020-07-13cs.SYeess.SYmath.OC

通过 Zonotope Scaling 实现不变、可行与判别核欠逼近

Invariant, Viability and Discriminating Kernel Under-Approximation via Zonotope Scaling

本文针对具有对抗输入的离散时间仿射动态系统，通过缩放中心-生成器形式的 zonotopes 并利用凸优化求解缩放因子，构造了欠逼近不变核、可行核和判别核的集合，实现了可扩展的安全验证。

2019-01-04cs.SYeess.SYmath.OC

A Kernel Mean Embedding Approach to Reducing Conservativeness in Stochastic Programming and Control

Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Freiburg（弗莱堡大学）

We apply kernel mean embedding methods to sample-based stochastic optimization and control. Specifically, we use the reduced-set expansion method as a way to discard sampled scenarios. The effect of such constraint removal is improved optimality and decreased conservativeness. This is achieved by solving a distributional-distance-regularized optimization problem. We demonstrated this optimization formulation is well-motivated in theory, computationally tractable and effective in numerical algorithms.

2020-04-22cs.LGcs.SYeess.SY

Worst-Case Risk Quantification under Distributional Ambiguity using Kernel Mean Embedding in Moment Problem

Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Freiburg（弗赖堡大学）

In order to anticipate rare and impactful events, we propose to quantify the worst-case risk under distributional ambiguity using a recent development in kernel methods -- the kernel mean embedding. Specifically, we formulate the generalized moment problem whose ambiguity set (i.e., the moment constraint) is described by constraints in the associated reproducing kernel Hilbert space in a nonparametric manner. We then present the tractable approximation and its theoretical justification. As a concrete application, we numerically test the proposed method in characterizing the worst-case constrai…

2020-09-06cs.LGcs.SYeess.SY

Hamilton-Jacobi 可行性分析用于对抗性不确定性下的约束垃圾焚烧系统安全运行

Hamilton-Jacobi Reachability for Viability Analysis of Constrained Waste-to-Energy Systems under Adversarial Uncertainty

LAMA Laboratory, Faculty of Sciences, Mohammed V University（拉巴特-萨莱-盖尼特拉大区穆罕默德五世大学理学院LAMA实验室）；College of Computing, Mohammed VI Polytechnic University（穆罕默德六世理工大学计算机学院）

本文研究在操作约束和不确定垃圾输入下维持垃圾焚烧系统安全运行的问题，提出基于Hamilton-Jacobi框架的鲁棒可行性方法，通过零和微分博弈模型，结合粘性HJB方程，为系统在最坏情况下保持在规定操作范围内提供保证。

2025-10-13math.OC

Data-Driven Chance Constrained Control using Kernel Distribution Embeddings

University of New Mexico（新墨西哥大学）；Stanford University（斯坦福大学）

We present a data-driven algorithm for efficiently computing stochastic control policies for general joint chance constrained optimal control problems. Our approach leverages the theory of kernel distribution embeddings, which allows representing expectation operators as inner products in a reproducing kernel Hilbert space. This framework enables approximately reformulating the original problem using a dataset of observed trajectories from the system without imposing prior assumptions on the parameterization of the system dynamics or the structure of the uncertainty. By optimizing over a finit…

2022-02-08cs.ROcs.SYeess.SY

Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control

University of New Mexico（新墨西哥大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）

Data-driven control algorithms use observations of system dynamics to construct an implicit model for the purpose of control. However, in practice, data-driven techniques often require excessive sample sizes, which may be infeasible in real-world scenarios where only limited observations of the system are available. Furthermore, purely data-driven methods often neglect useful a priori knowledge, such as approximate models of the system dynamics. We present a method to incorporate such prior knowledge into data-driven control algorithms using kernel embeddings, a nonparametric machine learning …

2023-01-09cs.LGcs.SYeess.SY

核均值嵌入拓扑：随机核的弱与强形式及其对模型学习的启示

Kernel Mean Embedding Topology: Weak and Strong Forms for Stochastic Kernels and Implications for Model Learning

Department of Mathematics, Bilkent University（巴勒莫大学数学系）；Department of Mathematics（数学系）；Statistics, Queen's University（皇后大学统计学系）

本文提出一种用于随机核的核均值嵌入拓扑（含弱与强形式），弱形式适用于松弛策略空间并揭示了与 Young 窄拓扑等的等价性质，强形式为模型空间提供拓扑表述并带来鲁棒性与学习理论启示，适用于研究最优性、近似与鲁棒性。

2025-10-31cs.LGcs.SYeess.SY

一种通过随机嵌入提高贝叶斯optimization鲁棒性的扭曲核

A warped kernel improving robustness in Bayesian optimization via random embeddings

该工作扩展了随机嵌入贝叶斯优化方法，通过在协方差核内集成高维子空间的翘曲。所提出的翘曲，依赖于基本的几何考虑，允许减轻高外在维度的缺点，同时避免算法评估点给出多余信息。它还简化了嵌入域的边界选择约束，从而提高了鲁棒性，如具有25个变量和内在维度6的测试用例所示。

2015-03-18math.OCstat.ML