Scott A. Smolka

Nicola Paoletti, Kin Sum Liu, Scott A. Smolka et al.

We present a fully closed-loop design for an artificial pancreas (AP) which regulates the delivery of insulin for the control of Type I diabetes. Our AP controller operates in a fully automated fashion, without requiring any manual interaction (e.g. in the form of meal announcements) with the patient. A major obstacle to achieving closed-loop insulin control is the uncertainty in those aspects of a patient's daily behavior that significantly affect blood glucose, especially in relation to meals and physical activity. To handle such uncertainties, we develop a data-driven robust model-predictive control framework, where we capture a wide range of individual meal and exercise patterns using uncertainty sets learned from historical data. These sets are then used in the controller and state estimator to achieve automated, precise, and personalized insulin therapy. We provide an extensive in silico evaluation of our robust AP design, demonstrating the potential of this approach, without explicit meal announcements, to support high carbohydrate disturbances and to regulate glucose levels in large clusters of virtual patients learned from population-wide survey data.

Usama Mehmood, Nicola Paoletti, Dung Phan et al.

The popularity of rule-based flocking models, such as Reynolds' classic flocking model, raises the question of whether more declarative flocking models are possible. This question is motivated by the observation that declarative models are generally simpler and easier to design, understand, and analyze than operational models. We introduce a very simple control law for flocking based on a cost function capturing cohesion (agents want to stay together) and separation (agents do not want to get too close). We refer to it as {\textit declarative flocking} (DF). We use model-predictive control (MPC) to define controllers for DF in centralized and distributed settings. A thorough performance comparison of our declarative flocking with Reynolds' model, and with more recent flocking models that use MPC with a cost function based on lattice structures, demonstrate that DF-MPC yields the best cohesion and least fragmentation, and maintains a surprisingly good level of geometric regularity while still producing natural flock shapes similar to those produced by Reynolds' model. We also show that DF-MPC has high resilience to sensor noise.

Scott A. Smolka, Ashish Tiwari, Lukas Esterle et al.

We introduce the concept of a V-formation game between a controller and an attacker, where controller's goal is to maneuver the plant (a simple model of flocking dynamics) into a V-formation, and the goal of the attacker is to prevent the controller from doing so. Controllers in V-formation games utilize a new formulation of model-predictive control we call Adaptive-Horizon MPC (AMPC), giving them extraordinary power: we prove that under certain controllability assumptions, an AMPC controller is able to attain V-formation with probability 1. We define several classes of attackers, including those that in one move can remove R birds from the flock, or introduce random displacement into flock dynamics. We consider both naive attackers, whose strategies are purely probabilistic, and AMPC-enabled attackers, putting them on par strategically with the controllers. While an AMPC-enabled controller is expected to win every game with probability 1, in practice, it is resource-constrained: its maximum prediction horizon and the maximum number of game execution steps are fixed. Under these conditions, an attacker has a much better chance of winning a V-formation game. Our extensive performance evaluation of V-formation games uses statistical model checking to estimate the probability an attacker can thwart the controller. Our results show that for the bird-removal game with R = 1, the controller almost always wins (restores the flock to a V-formation). For R = 2, the game outcome critically depends on which two birds are removed. For the displacement game, our results again demonstrate that an intelligent attacker, i.e. one that uses AMPC in this case, significantly outperforms its naive counterpart that randomly executes its attack.

Anna Lukina, Ashish Tiwari, Scott A. Smolka et al.

We present DAMPC, a distributed, adaptive-horizon and adaptive-neighborhood algorithm for solving the stochastic reachability problem in multi-agent systems, in particular flocking modeled as a Markov decision process. At each time step, every agent calls a centralized, adaptive-horizon model-predictive control (AMPC) algorithm to obtain an optimal solution for its local neighborhood. Second, the agents derive the flock-wide optimal solution through a sequence of consensus rounds. Third, the neighborhood is adaptively resized using a flock-wide, cost-based Lyapunov function V. This way DAMPC improves efficiency without compromising convergence. We evaluate DAMPC's performance using statistical model checking. Our results demonstrate that, compared to AMPC, DAMPC achieves considerable speed-up (two-fold in some cases) with only a slightly lower rate of convergence. The smaller average neighborhood size and lookahead horizon demonstrate the benefits of the DAMPC approach for stochastic reachability problems involving any controllable multi-agent system that possesses a cost function.

Dung Phan, Scott A. Smolka, Radu Grosu et al.

We present a novel approach to the problem of model checking cyber-physical systems. We transform the model checking problem to an optimization one by designing an objective function that measures how close a state is to a violation of a property. We use particle swarm optimization (PSO) to effectively search for a state that minimizes the objective function. Such states, if found, are counter-examples describing safe states from which the system can reach an unsafe state in one time step. We illustrate our approach with a controller for the Quickbot ground rover. Our PSO model checker quickly found a bug in the controller that could cause the rover to collide with an obstacle.

Sophie Gruenbacher, Mathias Lechner, Ramin Hasani et al.

We introduce a new stochastic verification algorithm that formally quantifies the behavioral robustness of any time-continuous process formulated as a continuous-depth model. Our algorithm solves a set of global optimization (Go) problems over a given time horizon to construct a tight enclosure (Tube) of the set of all process executions starting from a ball of initial states. We call our algorithm GoTube. Through its construction, GoTube ensures that the bounding tube is conservative up to a desired probability and up to a desired tightness. GoTube is implemented in JAX and optimized to scale to complex continuous-depth neural network models. Compared to advanced reachability analysis tools for time-continuous neural networks, GoTube does not accumulate overapproximation errors between time steps and avoids the infamous wrapping effect inherent in symbolic techniques. We show that GoTube substantially outperforms state-of-the-art verification tools in terms of the size of the initial ball, speed, time-horizon, task completion, and scalability on a large set of experiments. GoTube is stable and sets the state-of-the-art in terms of its ability to scale to time horizons well beyond what has been previously possible.

Usama Mehmood, Sanaz Sheikhi, Stanley Bak et al.

The Simplex Architecture is a runtime assurance framework where control authority may switch from an unverified and potentially unsafe advanced controller to a backup baseline controller in order to maintain the safety of an autonomous cyber-physical system. In this work, we show that runtime checks can replace the requirement to statically verify safety of the baseline controller. This is important as there are many powerful control techniques, such as model-predictive control and neural network controllers, that work well in practice but are difficult to statically verify. Since the method does not use internal information about the advanced or baseline controller, we call the approach the Black-Box Simplex Architecture. We prove the architecture is safe and present two case studies where (i) model-predictive control provides safe multi-robot coordination, and (ii) neural networks provably prevent collisions in groups of F-16 aircraft, despite the controllers occasionally outputting unsafe commands.

Sophie Gruenbacher, Ramin Hasani, Mathias Lechner et al.

We show that Neural ODEs, an emerging class of time-continuous neural networks, can be verified by solving a set of global-optimization problems. For this purpose, we introduce Stochastic Lagrangian Reachability (SLR), an abstraction-based technique for constructing a tight Reachtube (an over-approximation of the set of reachable states over a given time-horizon), and provide stochastic guarantees in the form of confidence intervals for the Reachtube bounds. SLR inherently avoids the infamous wrapping effect (accumulation of over-approximation errors) by performing local optimization steps to expand safe regions instead of repeatedly forward-propagating them as is done by deterministic reachability methods. To enable fast local optimizations, we introduce a novel forward-mode adjoint sensitivity method to compute gradients without the need for backpropagation. Finally, we establish asymptotic and non-asymptotic convergence rates for SLR.

Sophie Gruenbacher, Jacek Cyranka, Mathias Lechner et al.

We introduce LRT-NG, a set of techniques and an associated toolset that computes a reachtube (an over-approximation of the set of reachable states over a given time horizon) of a nonlinear dynamical system. LRT-NG significantly advances the state-of-the-art Langrangian Reachability and its associated tool LRT. From a theoretical perspective, LRT-NG is superior to LRT in three ways. First, it uses for the first time an analytically computed metric for the propagated ball which is proven to minimize the ball's volume. We emphasize that the metric computation is the centerpiece of all bloating-based techniques. Secondly, it computes the next reachset as the intersection of two balls: one based on the Cartesian metric and the other on the new metric. While the two metrics were previously considered opposing approaches, their joint use considerably tightens the reachtubes. Thirdly, it avoids the "wrapping effect" associated with the validated integration of the center of the reachset, by optimally absorbing the interval approximation in the radius of the next ball. From a tool-development perspective, LRT-NG is superior to LRT in two ways. First, it is a standalone tool that no longer relies on CAPD. This required the implementation of the Lohner method and a Runge-Kutta time-propagation method. Secondly, it has an improved interface, allowing the input model and initial conditions to be provided as external input files. Our experiments on a comprehensive set of benchmarks, including two Neural ODEs, demonstrates LRT-NG's superior performance compared to LRT, CAPD, and Flow*.

Hongkai Chen, Nicola Paoletti, Scott A. Smolka et al.

Even though model predictive control (MPC) is currently the main algorithm for insulin control in the artificial pancreas (AP), it usually requires complex online optimizations, which are infeasible for resource-constrained medical devices. MPC also typically relies on state estimation, an error-prone process. In this paper, we introduce a novel approach to AP control that uses Imitation Learning to synthesize neural-network insulin policies from MPC-computed demonstrations. Such policies are computationally efficient and, by instrumenting MPC at training time with full state information, they can directly map measurements into optimal therapy decisions, thus bypassing state estimation. We apply Bayesian inference via Monte Carlo Dropout to learn policies, which allows us to quantify prediction uncertainty and thereby derive safer therapy decisions. We show that our control policies trained under a specific patient model readily generalize (in terms of model parameters and disturbance distributions) to patient cohorts, consistently outperforming traditional MPC with state estimation.

Dung T. Phan, Radu Grosu, Nils Jansen et al.

We present the Neural Simplex Architecture (NSA), a new approach to runtime assurance that provides safety guarantees for neural controllers (obtained e.g. using reinforcement learning) of autonomous and other complex systems without unduly sacrificing performance. NSA is inspired by the Simplex control architecture of Sha et al., but with some significant differences. In the traditional approach, the advanced controller (AC) is treated as a black box; when the decision module switches control to the baseline controller (BC), the BC remains in control forever. There is relatively little work on switching control back to the AC, and there are no techniques for correcting the AC's behavior after it generates a potentially unsafe control input that causes a failover to the BC. Our NSA addresses both of these limitations. NSA not only provides safety assurances in the presence of a possibly unsafe neural controller, but can also improve the safety of such a controller in an online setting via retraining, without overly degrading its performance. To demonstrate NSA's benefits, we have conducted several significant case studies in the continuous control domain. These include a target-seeking ground rover navigating an obstacle field, and a neural controller for an artificial pancreas system.

Nicola Paoletti, Zhihao Jiang, Md Ariful Islam et al.

An Implantable Cardioverter Defibrillator (ICD) is a medical device used for the detection of potentially fatal cardiac arrhythmia and their treatment through the delivery of electrical shocks intended to restore normal heart rhythm. An ICD reprogramming attack seeks to alter the device's parameters to induce unnecessary shocks and, even more egregious, prevent required therapy. In this paper, we present a formal approach for the synthesis of ICD reprogramming attacks that are both effective, i.e., lead to fundamental changes in the required therapy, and stealthy, i.e., involve minimal changes to the nominal ICD parameters. We focus on the discrimination algorithm underlying Boston Scientific devices (one of the principal ICD manufacturers) and formulate the synthesis problem as one of multi-objective optimization. Our solution technique is based on an Optimization Modulo Theories encoding of the problem and allows us to derive device parameters that are optimal with respect to the effectiveness-stealthiness tradeoff (i.e., lie along the corresponding Pareto front). To the best of our knowledge, our work is the first to derive systematic ICD reprogramming attacks designed to maximize therapy disruption while minimizing detection. To evaluate our technique, we employ an extensive dataset of synthetic EGMs (cardiac signals), each generated with a prescribed arrhythmia, allowing us to synthesize attacks tailored to the victim's cardiac condition. Our approach readily generalizes to unseen signals, representing the unknown EGM of the victim patient.

Dung Phan, Nicola Paoletti, Timothy Zhang et al.

We introduce the State Classification Problem (SCP) for hybrid systems, and present Neural State Classification (NSC) as an efficient solution technique. SCP generalizes the model checking problem as it entails classifying each state $s$ of a hybrid automaton as either positive or negative, depending on whether or not $s$ satisfies a given time-bounded reachability specification. This is an interesting problem in its own right, which NSC solves using machine-learning techniques, Deep Neural Networks in particular. State classifiers produced by NSC tend to be very efficient (run in constant time and space), but may be subject to classification errors. To quantify and mitigate such errors, our approach comprises: i) techniques for certifying, with statistical guarantees, that an NSC classifier meets given accuracy levels; ii) tuning techniques, including a novel technique based on adversarial sampling, that can virtually eliminate false negatives (positive states classified as negative), thereby making the classifier more conservative. We have applied NSC to six nonlinear hybrid system benchmarks, achieving an accuracy of 99.25% to 99.98%, and a false-negative rate of 0.0033 to 0, which we further reduced to 0.0015 to 0 after tuning the classifier. We believe that this level of accuracy is acceptable in many practical applications, and that these results demonstrate the promise of the NSC approach.

Jacek Cyranka, Md. Ariful Islam, Scott A. Smolka et al.

We introduce continuous Lagrangian reachability (CLRT), a new algorithm for the computation of a tight and continuous-time reachtube for the solution flows of a nonlinear, time-variant dynamical system. CLRT employs finite strain theory to determine the deformation of the solution set from time $t_i$ to time $t_{i+1}$. We have developed simple explicit analytic formulas for the optimal metric for this deformation; this is superior to prior work, which used semi-definite programming. CLRT also uses infinitesimal strain theory to derive an optimal time increment $h_i$ between $t_i$ and $t_{i+1}$, nonlinear optimization to minimally bloat (i.e., using a minimal radius) the state set at time $t_i$ such that it includes all the states of the solution flow in the interval $[t_i,t_{i+1}]$. We use $δ$-satisfiability to ensure the correctness of the bloating. Our results on a series of benchmarks show that CLRT performs favorably compared to state-of-the-art tools such as CAPD in terms of the continuous reachtube volumes they compute.

Dung Phan, Radu Grosu, Nicola Paoletti et al.

We show how machine-learning techniques, particularly neural networks, offer a very effective and highly efficient solution to the approximate model-checking problem for continuous and hybrid systems, a solution where the general-purpose model checker is replaced by a model-specific classifier trained by sampling model trajectories. To the best of our knowledge, we are the first to establish this link from machine learning to model checking. Our method comprises a pipeline of analysis techniques for estimating and obtaining statistical guarantees on the classifier's prediction performance, as well as tuning techniques to improve such performance. Our experimental evaluation considers the time-bounded reachability problem for three well-established benchmarks in the hybrid systems community. On these examples, we achieve an accuracy of 99.82% to 100% and a false-negative rate (incorrectly predicting that unsafe states are not reachable from a given state) of 0.0007 to 0. We believe that this level of accuracy is acceptable in many practical applications and we show how the approximate model checker can be made more conservative by tuning the classifier through further training and selection of the classification threshold.

Fedor Shmarov, Nicola Paoletti, Ezio Bartocci et al.

We present a new method for the automated synthesis of safe and robust Proportional-Integral-Derivative (PID) controllers for stochastic hybrid systems. Despite their widespread use in industry, no automated method currently exists for deriving a PID controller (or any other type of controller, for that matter) with safety and performance guarantees for such a general class of systems. In particular, we consider hybrid systems with nonlinear dynamics (Lipschitz-continuous ordinary differential equations) and random parameters, and we synthesize PID controllers such that the resulting closed-loop systems satisfy safety and performance constraints given as probabilistic bounded reachability properties. Our technique leverages SMT solvers over the reals and nonlinear differential equations to provide formal guarantees that the synthesized controllers satisfy such properties. These controllers are also robust by design since they minimize the probability of reaching an unsafe state in the presence of random disturbances. We apply our approach to the problem of insulin regulation for type 1 diabetes, synthesizing controllers with robust responses to large random meal disturbances, thereby enabling them to maintain blood glucose levels within healthy, safe ranges.

Jacek Cyranka, Md. Ariful Islam, Greg Byrne et al.

We introduce LRT, a new Lagrangian-based ReachTube computation algorithm that conservatively approximates the set of reachable states of a nonlinear dynamical system. LRT makes use of the Cauchy-Green stretching factor (SF), which is derived from an over-approximation of the gradient of the solution flows. The SF measures the discrepancy between two states propagated by the system solution from two initial states lying in a well-defined region, thereby allowing LRT to compute a reachtube with a ball-overestimate in a metric where the computed enclosure is as tight as possible. To evaluate its performance, we implemented a prototype of LRT in C++/Matlab, and ran it on a set of well-established benchmarks. Our results show that LRT compares very favorably with respect to the CAPD and Flow* tools.

Anna Lukina, Lukas Esterle, Christian Hirsch et al.

We introduce ARES, an efficient approximation algorithm for generating optimal plans (action sequences) that take an initial state of a Markov Decision Process (MDP) to a state whose cost is below a specified (convergence) threshold. ARES uses Particle Swarm Optimization, with adaptive sizing for both the receding horizon and the particle swarm. Inspired by Importance Splitting, the length of the horizon and the number of particles are chosen such that at least one particle reaches a next-level state, that is, a state where the cost decreases by a required delta from the previous-level state. The level relation on states and the plans constructed by ARES implicitly define a Lyapunov function and an optimal policy, respectively, both of which could be explicitly generated by applying ARES to all states of the MDP, up to some topological equivalence relation. We also assess the effectiveness of ARES by statistically evaluating its rate of success in generating optimal plans. The ARES algorithm resulted from our desire to clarify if flying in V-formation is a flocking policy that optimizes energy conservation, clear view, and velocity alignment. That is, we were interested to see if one could find optimal plans that bring a flock from an arbitrary initial state to a state exhibiting a single connected V-formation. For flocks with 7 birds, ARES is able to generate a plan that leads to a V-formation in 95% of the 8,000 random initial configurations within 63 seconds, on average. ARES can also be easily customized into a model-predictive controller (MPC) with an adaptive receding horizon and statistical guarantees of convergence. To the best of our knowledge, our adaptive-sizing approach is the first to provide convergence guarantees in receding-horizon techniques.

Hung Pham, Scott A. Smolka, Scott D. Stoller et al.

Collision avoidance is a key factor in enabling the integration of unmanned aerial vehicle into real life use, whether it is in military or civil application. For a long time there have been a large number of works to address this problem; therefore a comparative summary of them would be desirable. This paper presents a survey on the major collision avoidance systems developed in up to date publications. Each collision avoidance system contains two main parts: sensing and detection, and collision avoidance. Based on their characteristics each part is divided into different categories; and those categories are explained, compared and discussed about advantages and disadvantages in this paper.

Kenan Kalajdzic, Cyrille Jegourel, Ezio Bartocci et al.

We introduce feedback-control statistical system checking (FC-SSC), a new approach to statistical model checking that exploits principles of feedback-control for the analysis of cyber-physical systems (CPS). FC-SSC uses stochastic system identification to learn a CPS model, importance sampling to estimate the CPS state, and importance splitting to control the CPS so that the probability that the CPS satisfies a given property can be efficiently inferred. We illustrate the utility of FC-SSC on two example applications, each of which is simple enough to be easily understood, yet complex enough to exhibit all of FC-SCC's features. To the best of our knowledge, FC-SSC is the first statistical system checker to efficiently estimate the probability of rare events in realistic CPS applications or in any complex probabilistic program whose model is either not available, or is infeasible to derive through static-analysis techniques.

Md. Ariful Islam, Richard DeFrancisco, Chuchu Fan et al.

We present what we believe to be the first formal verification of a biologically realistic (nonlinear ODE) model of a neural circuit in a multicellular organism: Tap Withdrawal (TW) in \emph{C. Elegans}, the common roundworm. TW is a reflexive behavior exhibited by \emph{C. Elegans} in response to vibrating the surface on which it is moving; the neural circuit underlying this response is the subject of this investigation. Specifically, we perform reachability analysis on the TW circuit model of Wicks et al. (1996), which enables us to estimate key circuit parameters. Underlying our approach is the use of Fan and Mitra's recently developed technique for automatically computing local discrepancy (convergence and divergence rates) of general nonlinear systems. We show that the results we obtain are in agreement with the experimental results of Wicks et al. (1995). As opposed to the fixed parameters found in most biological models, which can only produce the predominant behavior, our techniques characterize ranges of parameters that produce (and do not produce) all three observed behaviors: reversal of movement, acceleration, and lack of response.