# Sriram SankaranarayananUniversity of Colorado Boulder | CUB · Department of Computer Science (CS)

Sriram Sankaranarayanan

PhD

## About

188

Publications

18,429

Reads

**How we measure 'reads'**

A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more

5,908

Citations

Introduction

Additional affiliations

August 2009 - present

August 2009 - August 2015

October 2005 - August 2009

## Publications

Publications (188)

In this paper, we use the concept of artificial risk fields to predict how human operators control a vehicle in response to upcoming road situations. A risk field assigns a non-negative risk measure to the state of the system in order to model how close that state is to violating a safety property, such as hitting an obstacle or exiting the road. U...

This paper studies the problem of range analysis for feedforward neural networks, which is a basic primitive for applications such as robustness of neural networks, compliance to specifications and reachability analysis of neural-network feedback systems. Our approach focuses on ReLU (rectified linear unit) feedforward neural nets that present spec...

In this paper, we propose a framework to repair a pre-trained feed-forward neural network (NN) to satisfy a set of properties. We formulate the properties as a set of predicates that impose constraints on the output of NN over the target input domain. We define the NN repair problem as a Mixed Integer Quadratic Program (MIQP) to adjust the weights...

We propose a predictive runtime monitoring framework that forecasts the distribution of future positions of mobile robots in order to detect and avoid impending property violations such as collisions with obstacles or other agents. Our approach uses a restricted class of temporal logic formulas to represent the likely intentions of the agents along...

Information leaks via side channels remain a challenging problem to guarantee confidentiality. Static analysis is a prevalent approach for detecting side channels. However, the side-channel analysis poses challenges to the static techniques since they arise from non-functional aspects of systems and require an analysis of multiple traces. In additi...

This paper studies the problem of range analysis for feedforward neural networks, which is a basic primitive for applications such as robustness of neural networks, compliance to specifications and reachability analysis of neural-network feedback systems. Our approach focuses on ReLU (rectified linear unit) feedforward neural nets that present spec...

In this paper, we propose a method for bounding the probability that a stochastic differential equation (SDE) system violates a safety specification over the infinite time horizon. SDEs are mathematical models of stochastic processes that capture how states evolve continuously in time. They are widely used in numerous applications such as engineere...

In this paper, we study efficient approaches to reachability analysis for discrete-time nonlinear dynamical systems when the dependencies among the variables of the system have low treewidth. Reachability analysis over nonlinear dynamical systems asks if a given set of target states can be reached, starting from an initial set of states. This is so...

In this paper, we propose a method for bounding the probability that a stochastic differential equation (SDE) system violates a safety specification over the infinite time horizon. SDEs are mathematical models of stochastic processes that capture how states evolve continuously in time. They are widely used in numerous applications such as engineere...

Background:
Considering current insulin action profiles and the nature of glycemic responses to insulin, there is an acute need for longer-term, accurate, blood glucose predictions to inform insulin dosing schedules and enable effective decision support for the treatment of type 1 diabetes (T1D). However, current methods achieve acceptable accurac...

Control Barrier Functions (CBF) have been recently utilized in the design of provably safe feedback control laws for nonlinear systems. These feedback control methods typically compute the next control input by solving an online Quadratic Program (QP). Solving QP in real-time can be a computationally expensive process for resource constraint system...

We propose a predictive runtime monitoring approach for linear systems with stochastic disturbances. The goal of the monitor is to decide if there exists a possible sequence of control inputs over a given time horizon to ensure that a safety property is maintained with a sufficiently high probability. We derive an efficient algorithm for performing...

Logical specifications have enabled formal methods by carefully describing what is correct, desired or expected of a given system. They have been widely used in runtime monitoring and applied to domains ranging from medical devices to information security. In this tutorial, we will present the theory and application of robustness of logical specifi...

Detection and quantification of information leaks through timing side channels are important to guarantee confidentiality. Although static analysis remains the prevalent approach for detecting timing side channels, it is computationally challenging for real-world applications. In addition, the detection techniques are usually restricted to “yes” or...

Autonomous systems such as “self-driving” vehicles and closed-loop medical devices increasingly rely on learning-enabled components such as neural networks to perform safety critical perception and control tasks. As a result, the problem of verifying that these systems operate correctly is of the utmost importance. We will briefly examine the role...

In this paper, we study the template polyhedral abstract domain using connections to bilinear optimization techniques. The connections between abstract interpretation and convex optimization approaches have been studied for nearly a decade now. Specifically, data flow constraints for numerical domains such as polyhedra can be expressed in terms of...

We investigate approximate Bayesian inference techniques for nonlinear systems described by ordinary differential equation (ODE) models. In particular, the approximations will be based on set-valued reachability analysis approaches, yielding approximate models for the posterior distribution. Nonlinear ODEs are widely used to mathematically describe...

Detection and quantification of information leaks through timing side channels are important to guarantee confidentiality. Although static analysis remains the prevalent approach for detecting timing side channels, it is computationally challenging for real-world applications. In addition, the detection techniques are usually restricted to 'yes' or...

In this chapter, we present the interplay between models of human physiology, closed-loop medical devices, correctness specifications, and verification algorithms in the context of the artificial pancreas. The artificial pancreas refers to a series of increasingly sophisticated closed-loop medical devices that automate the delivery of insulin to pe...

Modern cyber-physical systems (CPS) are often developed in a model-based development (MBD) paradigm. The MBD paradigm involves the construction of different kinds of models: (1) a plant model that encapsulates the physical components of the system (e.g., mechanical, electrical, chemical components) using representations based on differential and al...

We present an approach to construct reachable set overapproximations for continuous-time dynamical systems controlled using neural network feedback systems. Feedforward deep neural networks are now widely used as a means for learning control laws through techniques such as reinforcement learning and data-driven predictive control. However, the lear...

We consider the problem of learning structured, closed-loop policies (feedback laws) from demonstrations in order to control under-actuated robotic systems, so that formal behavioral specifications such as reaching a target set of states are satisfied. Our approach uses a ``counterexample-guided'' iterative loop that involves the interaction betwee...

Continuous glucose monitors (CGM) display real-time glucose values enabling greater glycemic awareness with reduced management burden. Factory-calibrated CGM systems allow for glycemic assessment without the pain and inconvenience of fingerstick glucose testing. Advances in sensor chemistry and CGM algorithms have enabled factory-calibrated systems...

We present a technique for learning control Lyapunov-like functions, which are used in turn to synthesize controllers for nonlinear dynamical systems that can stabilize the system, or satisfy specifications such as remaining inside a safe set, or eventually reaching a target set while remaining inside a safe set. The learning framework uses a demon...

Semidefinite programming (SDP) solvers are increasingly used as primitives in many program verification tasks to synthesize and verify polynomial invariants for a variety of systems including programs, hybrid systems and stochastic models. On one hand, they provide a tractable alternative to reasoning about semi-algebraic constraints. However, the...

We present an approach to path following using so-called control funnel functions. Synthesizing controllers to "robustly" follow a reference trajectory is a fundamental problem for autonomous vehicles. Robustness, in this context, requires our controllers to handle a specified amount of deviation from the desired trajectory. Our approach considers...

This paper presents a case study of a data driven approach to verification and parameter synthesis for artificial pancreas control systems which deliver insulin to patients with type-1 diabetes (T1D). We present a new approach to tuning parameters using non-deterministic data-driven models for human insulin-glucose regulation, which are inferred fr...

The term Cyber-Physical Systems (CPS) typically refers to engineered, physical and biological systems monitored and/or controlled by an embedded computational core. The behaviour of a CPS over time is generally characterised by the evolution of physical quantities, and discrete software and hardware states. In general, these can be mathematically m...

In this paper, we provide an approach to data-driven control for artificial
pancreas system by learning neural network models of human insulin-glucose physiology from available patient data and using a mixed integer optimization approach to control blood glucose levels in real-time using the inferred models.
First, our approach learns neural networ...

We present an approach to learn and formally verify feedback laws for data-driven models of neural networks. Neural networks are emerging as powerful and general data-driven representations for functions. This has led to their increased use in data-driven plant models and the representation of feedback laws in control systems. However, it is hard t...

In this article, we consider the problem of synthesizing switching controllers for temporal properties through the composition of simple primitive reach-while-stay (RWS) properties. Reach-while-stay properties specify that the system states starting from an initial set I, must reach a goal (target) set G in finite time, while remaining inside a saf...

We propose techniques to construct abstractions for nonlinear dynamics in terms of relations expressed in linear arithmetic. Such relations are useful for translating the closed loop verification problem of control software with continuous-time, nonlinear plant models into discrete and linear models that can be handled by efficient software verific...

Deep neural networks (NN) are extensively used for machine learning tasks such as image classification, perception and control of autonomous systems. Increasingly, these deep NNs are also been deployed in high-assurance applications. Thus, there is a pressing need for developing techniques to verify neural networks to check whether certain user-exp...

In this paper, we draw upon connections between bilinear programming and the process of computing (post) fixed points in abstract interpretation. It is well-known that the data flow constraints for numerical domains are expressed in terms of bilinear constraints. Algorithms such as policy and strategy iteration have been proposed for the special ca...

As formal verification techniques for cyber-physical systems encounter large plant models, techniques for simplifying these models into smaller approximate models are gaining increasing popularity. Model-order reduction techniques take large ordinary differential equation models and simplify them to yield models that are potentially much smaller in...

In this paper, we consider the problem of synthesizing static output feedback controllers for stabilizing polynomial systems. We jointly synthesize a Lyapunov function and a static output feedback controller that stabilizes the system over a given subset of the state-space. Motivated by the numerical issues that are commonly faced using SOS (Sum of...

In this paper we prove the convergence of an algorithm synthesising continuous piecewise-polynomial Lyapunov functions for polynomial vector fields defined on simplices. We subsequently modify the algorithm to sub-divide locally by utilizing information from infeasible linear problems. We prove that this modification does not destroy the convergenc...

We present a technique for learning control Lyapunov (potential) functions, which are used in turn to synthesize controllers for nonlinear dynamical systems. The learning framework uses a demonstrator that implements a black-box, untrusted strategy presumed to solve the problem of interest, a learner that poses finitely many queries to the demonstr...

We study the problem of analyzing falsifying traces of cyber-physical systems. Specifically, given a system model and an input which is a counterexample to a property of interest, we wish to understand which parts of the inputs are "responsible" for the counterexample as a whole. Whereas this problem is well known to be hard to solve precisely, we...

What properties about the internals of a program explain the possible differences in its overall running time for different inputs? In this paper, we propose a formal framework for considering this question we dub trace-set discrimination. We show that even though the algorithmic problem of computing maximum likelihood discriminants is NP-hard, app...

We present a model-based falsification scheme for artificial pancreas controllers. Our approach performs a closed-loop simulation of the control software using models of the human insulin-glucose regulatory system. Our work focuses on testing properties of an overnight control system for hypoglycemia/hyperglycemia minimization in patients with type...

What properties about the internals of a program explain the possible differences in its overall running time for different inputs? In this paper, we propose a formal framework for considering this question we dub trace-set discrimination. We show that even though the algorithmic problem of computing maximum likelihood discriminants is NP-hard, app...

We investigate the problem of synthesizing robust controllers that ensure that the closed loop satisfies an input reach-while-stay specification, wherein all trajectories starting from some initial set I, eventually reach a specified goal set G, while staying inside a safe set S. Our plant model consists of a continuous-time switched system control...

Semidefinite programming (SDP) solvers are increasingly used as primitives in many program verification tasks to synthesize and verify polynomial invariants for a variety of systems including programs, hybrid systems and stochastic models. On one hand, they provide a tractable alternative to reasoning about semi-algebraic constraints. However, the...

We study the problem of falsifying reachability properties of real-time control software acting in a closed-loop with a given model of the plant dynamics. Our approach employs numerical techniques to simulate a plant model, which may be highly nonlinear and hybrid, in combination with symbolic simulation of the controller software. The state-space...

We consider the problem of reasoning about the probability of assertion violations in straight-line, nonlinear computations involving uncertain quantities modeled as random variables. Such computations are quite common in many areas such as cyber-physical systems and numerical computation. Our approach extends probabilistic affine forms, an interva...

Martingale theory yields a powerful set of tools that have recently been used to prove quantitative properties of stochastic systems such as stochas-tic safety and qualitative properties such as almost sure termination. In this paper , we examine proof techniques for establishing almost sure persistence and recurrence properties of infinite-state d...

In this article, the problem of synthesizing switching controllers is considered through the synthesis of a "control certificate". Control certificates include control barrier and Lyapunov functions, which represent control strategies, and allow for automatic controller synthesis. Our approach encodes the controller synthesis problem as quantified...

Latest developments brought interesting theoretical results and powerful tools for the reachability analysis of hybrid systems. However, there are still challenging problems to be solved in order to make those technologies applicable to large-scale applications in industrial context. To support this development, in this paper we give a brief overvi...

We investigate the problem of synthesizing switching controllers for stabilizing continuous-time plants. First, we introduce a class of control Lyapunov functions (CLFs) for switched systems along with a switching strategy that yields a closed loop system with a guaranteed minimum dwell time in each switching mode. However, the challenge lies in au...

In this paper, we examine linear programming (LP) relaxations based on
Bernstein polynomials for polynomial optimization problems (POPs). We present a
progression of increasingly more precise LP relaxations based on expressing the
given polynomial in its Bernstein form, as a linear combination of Bernstein
polynomials. The well-known bounds on Bern...

We introduce a counter-example guided inductive synthesis (CEGIS) framework
for synthesizing continuous-time switching controllers that guarantee reach
while stay (RWS) properties of the closed loop system. The solution is based on
synthesizing specially defined class of control Lyapunov functions (CLFs) for
switched systems, that yield switching c...

In this work, we examine relaxations for the stability analysis and synthesis of stabilizing controllers for polynomial dynamical systems. It is well-known that such problems can be naturally solved using a reduction to polynomial optimization problems. The Sum of Squares (SOS) programming relaxation further relaxes these polynomial optimization pr...

In this project, we address the problem of synthesizing region-stabilizing controllers for switched systems. The plant model consists of a continuous-time switched system with finitely many switching modes. Our approach searches for a state-feedback that chooses between finitely many switching modes at each time instant: (a) guaranteeing a minimum...

We present a search technique to falsify safety properties of hybrid systems that model a software system controlling a physical plant. Our approach takes as input (a) the controller code and (b) a plant model given as a black-box system that can be simulated for given inputs over finite time horizons. Our approach combines the symbolic execution o...

In this paper, we deal with the problem of synthesizing static output
feedback controllers for stabilizing polynomial systems. Our approach jointly
synthesizes a Lyapunov function and a static output feedback controller that
stabilizes the system over a given subset of the state-space. Specifically, our
approach is simultaneously targeted towards t...