arXiv subjects

Bai Xue

Publications and source records attributed to Bai Xue.

At least 37 records · Page 2Linked to original sources

arXiv2024

Synthesizing Invariants for Polynomial Programs by Semidefinite Programming

Constraint-solving-based program invariant synthesis takes a parametric invariant template and encodes the (inductive) invariant conditions into constraints. The problem of characterizing the set of all valid parameter assignments is referred to as the strong invariant synthesis problem, while the problem of finding a concrete valid parameter assignment is called the weak invariant synthesis problem. For both problems, the challenge lies in solving or reducing the encoded constraints, which are generally non-convex and lack efficient solvers. Consequently, existing works either rely on heuristic optimization techniques (such as bilinear matrix inequalities) or resort to general-purpose solvers (such as quantifier elimination), leading to a trade-off between completeness and efficiency. In this paper, we propose two novel algorithms for synthesizing invariants of polynomial programs using semidefinite programming (SDP): (1) The Cluster algorithm targets the strong invariant synthesis problem for polynomial invariant templates. Leveraging robust optimization techniques, it solves a series of SDP relaxations and yields a sequence of increasingly precise under-approximations of the set of valid parameter assignments. We prove the algorithm's soundness, convergence, and weak completeness under a specific robustness assumption on templates. Moreover, the outputs can simplify the weak invariant synthesis problem. (2) The Mask algorithm addresses the weak invariant synthesis problem in scenarios where the aforementioned robustness assumption does not hold, rendering the Cluster algorithm ineffective. It identifies a specific subclass of invariant templates, termed masked templates, involving parameterized polynomial equalities and known inequalities. By applying variable substitution, the algorithm transforms constraints into an equivalent form amenable to SDP relaxations.

cs.PL↗

arXiv2024

A Framework for Safe Probabilistic Invariance Verification of Stochastic Dynamical Systems

Ensuring safety through set invariance has proven to be a valuable method in various robotics and control applications. This paper introduces a comprehensive framework for the safe probabilistic invariance verification of both discrete- and continuous-time stochastic dynamical systems over an infinite time horizon. The objective is to ascertain the lower and upper bounds of liveness probabilities for a given safe set and set of initial states. The liveness probability signifies the likelihood of the system remaining within the safe set indefinitely, starting from a state in the initial set. To address this problem, we propose optimizations for verifying safe probabilistic invariance in discrete-time and continuous-time stochastic dynamical systems. These optimizations are constructed via either using the Doob's nonnegative supermartingale inequality-based method or relaxing the equations described in [30,32], which can precisely characterize the probability of reaching a target set while avoiding unsafe states. Finally, we demonstrate the effectiveness of these optimizations through several examples using semi-definite programming tools.

eess.SY↗

arXiv2024

Inner-approximate Reachability Computation via Zonotopic Boundary Analysis

Inner-approximate reachability analysis involves calculating subsets of reachable sets, known as inner-approximations. This analysis is crucial in the fields of dynamic systems analysis and control theory as it provides a reliable estimation of the set of states that a system can reach from given initial states at a specific time instant. In this paper, we study the inner-approximate reachability analysis problem based on the set-boundary reachability method for systems modelled by ordinary differential equations, in which the computed inner-approximations are represented with zonotopes. The set-boundary reachability method computes an inner-approximation by excluding states reached from the initial set's boundary. The effectiveness of this method is highly dependent on the efficient extraction of the exact boundary of the initial set. To address this, we propose methods leveraging boundary and tiling matrices that can efficiently extract and refine the exact boundary of the initial set represented by zonotopes. Additionally, we enhance the exclusion strategy by contracting the outer-approximations in a flexible way, which allows for the computation of less conservative inner-approximations. To evaluate the proposed method, we compare it with state-of-the-art methods against a series of benchmarks. The numerical results demonstrate that our method is not only efficient but also accurate in computing inner-approximations.

eess.SY↗

arXiv2024

UR4NNV: Neural Network Verification, Under-approximation Reachability Works!

Recently, formal verification of deep neural networks (DNNs) has garnered considerable attention, and over-approximation based methods have become popular due to their effectiveness and efficiency. However, these strategies face challenges in addressing the "unknown dilemma" concerning whether the exact output region or the introduced approximation error violates the property in question. To address this, this paper introduces the UR4NNV verification framework, which utilizes under-approximation reachability analysis for DNN verification for the first time. UR4NNV focuses on DNNs with Rectified Linear Unit (ReLU) activations and employs a binary tree branch-based under-approximation algorithm. In each epoch, UR4NNV under-approximates a sub-polytope of the reachable set and verifies this polytope against the given property. Through a trial-and-error approach, UR4NNV effectively falsifies DNN properties while providing confidence levels when reaching verification epoch bounds and failing falsifying properties. Experimental comparisons with existing verification methods demonstrate the effectiveness and efficiency of UR4NNV, significantly reducing the impact of the "unknown dilemma".

cs.AI↗

arXiv2023

Reach-Avoid Analysis for Polynomial Stochastic Differential Equations

In this paper we propose a novel semi-definite programming approach that solves reach-avoid problems over open (i.e., not bounded a priori) time horizons for dynamical systems modeled by polynomial stochastic differential equations. The reach-avoid problem in this paper is a probabilistic guarantee: we approximate from the inner a $p$-reach-avoid set, i.e., the set of initial states guaranteeing with probability larger than $p$ that the system eventually enters a given target set while remaining inside a specified safe set till the target hit. Our approach begins with the construction of a bounded value function, whose strict $p$ super-level set is equal to the $p$-reach-avoid set. This value function is then reduced to a twice continuously differentiable solution to a system of equations. The system of equations facilitates the construction of a semi-definite program using sum-of-squares decomposition for multivariate polynomials and thus the transformation of nonconvex reach-avoid problems into a convex optimization problem. The semi-definite program can be solved efficiently in polynomial time with many existing powerful algorithms such as interior point methods and off-the-shelf software packages. We would like to point out that our approach can straightforwardly be specialized to address classical safety verification by, a.o., stochastic barrier certificate methods and reach-avoid analysis for ordinary differential equations. In addition, several examples are provided to demonstrate theoretical and algorithmic developments of the proposed method.

math.OC↗

arXiv2023

Scenario Approach for Parametric Markov Models

In this paper, we propose an approximating framework for analyzing parametric Markov models. Instead of computing complex rational functions encoding the reachability probability and the reward values of the parametric model, we exploit the scenario approach to synthesize a relatively simple polynomial approximation. The approximation is probably approximately correct (PAC), meaning that with high confidence, the approximating function is close to the actual function with an allowable error. With the PAC approximations, one can check properties of the parametric Markov models. We show that the scenario approach can also be used to check PRCTL properties directly, without synthesizing the polynomial at first hand. We have implemented our algorithm in a prototype tool and conducted thorough experiments. The experimental results demonstrate that our tool is able to compute polynomials for more benchmarks than state of the art tools such as PRISM and Storm, confirming the efficacy of our PAC-based synthesis.

cs.LO↗

arXiv2023

Reach-avoid Analysis for Sampled-data Systems with Measurement Uncertainties

Digital control has become increasingly prevalent in modern systems, making continuous-time plants controlled by discrete-time (digital) controllers ubiquitous and crucial across industries, including aerospace, automotive, and manufacturing. This paper focuses on investigating the reach-avoid problem in such systems, where the objective is to reach a goal set while avoiding unsafe states, especially in the presence of state measurement uncertainties. We propose an approach that builds upon the concept of exponential control guidance barrier functions, originally used for synthesizing continuous-time feedback controllers. We introduce a sufficient condition that, if met by a given continuous-time feedback controller, ensures the safe guidance of the system into the goal set in its sampled-data implementation, despite state measurement uncertainties. The event of reaching the goal set is determined based on state measurements obtained at the sampling time instants. Numerical examples are provided to demonstrate the validity of our theoretical developments, showcasing successful implementation in solving the reach-avoid problem in sampled-data systems with state measurement uncertainties.

eess.SY↗

arXiv2023

Safe Exit Controllers Synthesis for Continuous-time Stochastic Systems

This paper tackles the problem of generating safe exit controllers for continuous-time systems described by stochastic differential equations (SDEs). The primary aim is to develop controllers that maximize the lower bounds of the exit probability that the system escapes from a safe but uncomfortable set within a specified time frame and guide it towards a comfortable set. The paper considers two distinct cases: one in which the boundary of the safe set is a subset of the boundary of the uncomfortable set, and the other where the boundaries of the two sets do not intersect. To begin, we present a sufficient condition for establishing lower bounds on the exit probability in the first case. This condition serves as a guideline for constructing an online linear programming problem. The linear programming problem is designed to implicitly synthesize an optimal exit controller that maximizes the lower bounds of the exit probability. The method employed in the first case is then extended to the second one. Finally, we demonstrate the effectiveness of the proposed approaches on one example.

eess.SY↗

arXiv2023

Correct-by-Construction for Hybrid Systems by Synthesizing Reset Controller

Controller synthesis, including reset controller, feedback controller, and switching logic controller, provides an essential mechanism to guarantee the correctness and reliability of hybrid systems in a correct-by-construction manner. Unfortunately, reset controller synthesis is still in an infant stage in the literature, although it makes theoretical and practical significance. In this paper, we propose a convex programming based method to synthesize reset controllers for polynomial hybrid systems subject to safety, possibly together with liveness. Such a problem essentially corresponds to computing an initial set of continuous states in each mode and a reset map associated with each discrete jump such that any trajectory starting from any computed initial state keeps safe if only safety constraints are given or reaches the target set eventually and keeps safe before that if both safety and liveness are given, through the computed reset maps. Both cases can be reduced to reach-avoid and/or differential invariant generation problems, further encoded as convex optimization problems. Finally, several examples are provided to demonstrate the efficiency and effectiveness of our method.

eess.SY↗

arXiv2023

Verifying Safety of Neural Networks from Topological Perspectives

Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their behaviors should undergo rigorous guarantees before deployment in practice. In this paper, we propose a set-boundary reachability method to investigate the safety verification problem of NNs from a topological perspective. Given an NN with an input set and a safe set, the safety verification problem is to determine whether all outputs of the NN resulting from the input set fall within the safe set. In our method, the homeomorphism property and the open map property of NNs are mainly exploited, which establish rigorous guarantees between the boundaries of the input set and the boundaries of the output set. The exploitation of these two properties facilitates reachability computations via extracting subsets of the input set rather than the entire input set, thus controlling the wrapping effect in reachability analysis and facilitating the reduction of computation burdens for safety verification. The homeomorphism property exists in some widely used NNs such as invertible residual networks (i-ResNets) and Neural ordinary differential equations (Neural ODEs), and the open map is a less strict property and easier to satisfy compared with the homeomorphism property. For NNs establishing either of these properties, our set-boundary reachability method only needs to perform reachability analysis on the boundary of the input set. Moreover, for NNs that do not feature these properties with respect to the input set, we explore subsets of the input set for establishing the local homeomorphism property and then abandon these subsets for reachability computations. Finally, some examples demonstrate the performance of the proposed method.

cs.LG↗

arXiv2023

Model Predictive Control with Reach-avoid Analysis

In this paper we investigate the optimal controller synthesis problem, so that the system under the controller can reach a specified target set while satisfying given constraints. Existing model predictive control (MPC) methods learn from a set of discrete states visited by previous (sub-)optimized trajectories and thus result in computationally expensive mixed-integer nonlinear optimization. In this paper a novel MPC method is proposed based on reach-avoid analysis to solve the controller synthesis problem iteratively. The reach-avoid analysis is concerned with computing a reach-avoid set which is a set of initial states such that the system can reach the target set successfully. It not only provides terminal constraints, which ensure feasibility of MPC, but also expands discrete states in existing methods into a continuous set (i.e., reach-avoid sets) and thus leads to nonlinear optimization which is more computationally tractable online due to the absence of integer variables. Finally, we evaluate the proposed method and make comparisons with state-of-the-art ones based on several examples.

math.OC↗

arXiv2023

Repairing Deep Neural Networks Based on Behavior Imitation

The increasing use of deep neural networks (DNNs) in safety-critical systems has raised concerns about their potential for exhibiting ill-behaviors. While DNN verification and testing provide post hoc conclusions regarding unexpected behaviors, they do not prevent the erroneous behaviors from occurring. To address this issue, DNN repair/patch aims to eliminate unexpected predictions generated by defective DNNs. Two typical DNN repair paradigms are retraining and fine-tuning. However, existing methods focus on the high-level abstract interpretation or inference of state spaces, ignoring the underlying neurons' outputs. This renders patch processes computationally prohibitive and limited to piecewise linear (PWL) activation functions to great extent. To address these shortcomings, we propose a behavior-imitation based repair framework, BIRDNN, which integrates the two repair paradigms for the first time. BIRDNN corrects incorrect predictions of negative samples by imitating the closest expected behaviors of positive samples during the retraining repair procedure. For the fine-tuning repair process, BIRDNN analyzes the behavior differences of neurons on positive and negative samples to identify the most responsible neurons for the erroneous behaviors. To tackle more challenging domain-wise repair problems (DRPs), we synthesize BIRDNN with a domain behavior characterization technique to repair buggy DNNs in a probably approximated correct style. We also implement a prototype tool based on BIRDNN and evaluate it on ACAS Xu DNNs. Our experimental results show that BIRDNN can successfully repair buggy DNNs with significantly higher efficiency than state-of-the-art repair tools. Additionally, BIRDNN is highly compatible with different activation functions.

cs.LG↗

arXiv2023

Provable Reach-avoid Controllers Synthesis Based on Inner-approximating Controlled Reach-avoid Sets

In this paper, we propose an approach for synthesizing provable reach-avoid controllers, which drive a deterministic system operating in an unknown environment to safely reach a desired target set. The approach falls within the reachability analysis framework and is based on the computation of inner-approximations of controlled reach-avoid sets(CRSs). Given a target set and a safe set, the controlled reach-avoid set is the set of states such that starting from each of them, there exists at least one controller to ensure that the system can enter the target set while staying inside the safe set before the target hitting time. Therefore, the boundary of the controlled reach-avoid set acts as a barrier, which separating states capable of achieving the reach-avoid objective from those that are not, and thus the computed inner-approximation provides a viable space for the system to achieve the reach-avoid objective. Our approach for synthesizing reach-avoid controllers mainly consists of three steps. We first learn a safe set of states in the unknown environment from sensor measurements based on a support vector machine approach. Then, based on the learned safe set and target set, we compute an inner-approximation of the CRS. Finally, we synthesize controllers online to ensure that the system will reach the target set by evolving inside the computed inner-approximation. The proposed method is demonstrated on a Dubin's car system.

eess.SY↗

arXiv2023

Reach-avoid Controllers Synthesis for Safety Critical Systems

In this paper we propose sufficient conditions to synthesizing reach-avoid controllers for deterministic systems modelled by ordinary differential equations and stochastic systems modeled by stochastic differential equations based on the notion of control guidance-barrier functions. We begin with considering deterministic systems. Given an open safe set, a target set and a nominal controller, we attempt to synthesize a reach-avoid controller, which modifies the nominal controller in a minimal way enforcing the reach-avoid objective, i.e., the system will enter the target set eventually while staying inside the safe set before the first target hitting time. Three control guidance-barrier functions are developed and three corresponding conditions for synthesizing reach-avoid controllers are constructed, which get progressively weaker and thus facilitate the optimal controller design. The first and second ones are termed exponential and asymptotic control guidance-barrier functions, which guarantee that every trajectory starting from the safe set will enter the target set respectively at an exponential rate and in an asymptotic way. However, it is observed that these two control guidance-barrier functions have one condition in common of enforcing invariance of its every positive sublevel set until the system enters the target set, which is strict and thus limits the space of admissible controllers. Consequently, a lax control guidance-barrier function is further developed such that only the safe set set is an invariance before the system enters the target set, expanding the space of admissible control inputs. Then, we extend the methodologies for deterministic systems to stochastic systems, which synthesize reach-avoid controllers in the probabilistic setting. Finally, several numerical examples demonstrate the performance of proposed methods.

eess.SY↗

arXiv2023

Reachability Verification for Stochastic Discrete-time Dynamical Systems

In this paper we study reachability verification problems of stochastic discrete-time dynamical systems over the infinite time horizon. The reachability verification of interest in this paper is to certify specified lower and upper bounds of the reachability probability, with which the system starting from a designated initial set will enter a desired target set eventually. Existing sufficient conditions for reachability verification over the infinite time horizon are established based on the Doob's non-supermartingle inequality, which are often restrictive. Recently, a set of equations was proposed in [18], to which the solution is able to characterize the exact reachability probability. Inspired by this result, we in this paper propose sufficient conditions for reachability verification based on relaxing this equation. These sufficient conditions are shown to be weaker than the state-of-the-art ones, consequently being capable of providing more opportunities for verifying the reachability property successfully.

eess.SY↗

arXiv2023

Reach-avoid Verification using Lyapunov Densities

Reach-avoid analysis combines the construction of safety and specific progress guarantees, and is able to formalize many important engineering problems. In this paper we study the reach-avoid verification problem of systems modelled by ordinary differential equations using Lyapunov densities. Firstly, the weak reach-avoid verification is considered. Given an initial set, a safe set and a target set, the weak reach-avoid verification is to verify whether the reach-avoid property (i.e., the system will enter the target set eventually while staying inside the safe set before the first target hitting time) holds for almost all states in the initial set. We propose two novel sufficient conditions using Lyapunov densities for the weak reach-avoid verification. These two sufficient conditions are shown to be weaker than existing ones, providing more possibilities of verifying weak reach-avoid properties successfully. Then, we generalize these conditions to the verification of reach-avoid properties for all states in the initial set. Finally, an example demonstrates theoretical developments of proposed conditions.

eess.SY↗

arXiv2022

Credit Assignment for Trained Neural Networks Based on Koopman Operator Theory

Credit assignment problem of neural networks refers to evaluating the credit of each network component to the final outputs. For an untrained neural network, approaches to tackling it have made great contributions to parameter update and model revolution during the training phase. This problem on trained neural networks receives rare attention, nevertheless, it plays an increasingly important role in neural network patch, specification and verification. Based on Koopman operator theory, this paper presents an alternative perspective of linear dynamics on dealing with the credit assignment problem for trained neural networks. Regarding a neural network as the composition of sub-dynamics series, we utilize step-delay embedding to capture snapshots of each component, characterizing the established mapping as exactly as possible. To circumvent the dimension-difference problem encountered during the embedding, a composition and decomposition of an auxiliary linear layer, termed minimal linear dimension alignment, is carefully designed with rigorous formal guarantee. Afterwards, each component is approximated by a Koopman operator and we derive the Jacobian matrix and its corresponding determinant, similar to backward propagation. Then, we can define a metric with algebraic interpretability for the credit assignment of each network component. Moreover, experiments conducted on typical neural networks demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2022

Safety Verification for Neural Networks Based on Set-boundary Analysis

Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their behaviors should undergo rigorous guarantees before deployment in practice. In this paper we propose a set-boundary reachability method to investigate the safety verification problem of NNs from a topological perspective. Given an NN with an input set and a safe set, the safety verification problem is to determine whether all outputs of the NN resulting from the input set fall within the safe set. In our method, the homeomorphism property of NNs is mainly exploited, which establishes a relationship mapping boundaries to boundaries. The exploitation of this property facilitates reachability computations via extracting subsets of the input set rather than the entire input set, thus controlling the wrapping effect in reachability analysis and facilitating the reduction of computation burdens for safety verification. The homeomorphism property exists in some widely used NNs such as invertible NNs. Notable representations are invertible residual networks (i-ResNets) and Neural ordinary differential equations (Neural ODEs). For these NNs, our set-boundary reachability method only needs to perform reachability analysis on the boundary of the input set. For NNs which do not feature this property with respect to the input set, we explore subsets of the input set for establishing the local homeomorphism property, and then abandon these subsets for reachability computations. Finally, some examples demonstrate the performance of the proposed method.

cs.AI↗