Abstract We present a major new version of Scenic, a probabilistic programming language for writing formal models of the environments of cyber-physical systems. Scenic has been successfully used for the design and analysis of CPS in a variety of domains, but earlier versions are limited to environments that are essentially two-dimensional. In this paper, we extend Scenic with native support for 3D geometry, introducing new syntax that provides expressive ways to describe 3D configurations while preserving the simplicity and readability of the language. We replace Scenic’s simplistic representation of objects as boxes with precise modeling of complex shapes, including a ray tracing-based visibility system that accounts for object occlusion. We also extend the language to support arbitrary temporal requirements expressed in LTL, and build an extensible Scenic parser generated from a formal grammar of the language. Finally, we illustrate the new application domains these features enable with case studies that would have been impossible to accurately model in Scenic 2.

Abstract We propose a new probabilistic programming language for the design and analysis of cyber-physical systems, especially those based on machine learning. We consider several problems arising in the design process, including training a system to be robust to rare events, testing its performance under different conditions, and debugging failures. We show how a probabilistic programming language can help address these problems by specifying distributions encoding interesting types of inputs, then sampling these to generate specialized training and test data. More generally, such languages can be used to write environment models, an essential prerequisite to any formal analysis. In this paper, we focus on systems such as autonomous cars and robots, whose environment at any point in time is a scene , a configuration of physical objects and agents. We design a domain-specific language, Scenic , for describing scenarios that are distributions over scenes and the behaviors of their agents over time. Scenic combines concise, readable syntax for spatiotemporal relationships with the ability to declaratively impose hard and soft constraints over the scenario. We develop specialized techniques for sampling from the resulting distribution, taking advantage of the structure provided by Scenic ’s domain-specific syntax. Finally, we apply Scenic in multiple case studies for training, testing, and debugging neural networks for perception both as standalone components and within the context of a full cyber-physical system.

We present VerifAI , a software toolkit for the formal design and analysis of systems that include artificial intelligence (AI) and machine learning (ML) components. VerifAI particularly addresses challenges with applying formal methods to ML components such as perception systems based on deep neural networks, as well as systems containing them, and to model and analyze system behavior in the presence of environment uncertainty. We describe the initial version of VerifAI , which centers on simulation-based verification and synthesis, guided by formal models and specifications. We give examples of several use cases, including temporal-logic falsification, model-based systematic fuzz testing, parameter synthesis, counterexample analysis, and data set augmentation.

The recent drive towards achieving greater autonomy and intelligence in robotics has led to high levels of complexity. Autonomous robots increasingly depend on third-party off-the-shelf components and complex machine-learning techniques. This trend makes it challenging to provide strong design-time certification of correct operation. To address these challenges, we present SOTER, a robotics programming framework with two key components: (1) a programming language for implementing and testing high-level reactive robotics software, and (2) an integrated runtime assurance (RTA) system that helps enable the use of uncertified components, while still providing safety guarantees. SOTER provides language primitives to declaratively construct a RTA module consisting of an advanced, high-performance controller (uncertified), a safe, lower-performance controller (certified), and the desired safety specification. The framework provides a formal guarantee that a well-formed RTA module always satisfies the safety specification, without completely sacrificing performance by using higher performance uncertified components whenever safe. SOTER allows the complex robotics software stack to be constructed as a composition of RTA modules, where each uncertified component is protected using a RTA module. To demonstrate the efficacy of our framework, we consider a real-world case-study of building a safe drone surveillance system. Our experiments both in simulation and on actual drones show that the SOTER-enabled RTA ensures the safety of the system, including when untrusted third-party components have bugs or deviate from the desired behavior.

We consider the problem of extracting safe environments and controllers for reach-avoid objectives for systems with known state and control spaces, but unknown dynamics. In a given environment, a common approach is to synthesize a controller from an abstraction or a model of the system (potentially learned from data). However, in many situations, the relationship between the dynamics of the model and the actual system is not known; and hence it is difficult to provide safety guarantees for the system. In such cases, the Standard Simulation Metric (SSM), defined as the worst-case norm distance between the model and the system output trajectories, can be used to modify a reach-avoid specification for the system into a more stringent specification for the abstraction. Nevertheless, the obtained distance, and hence the modified specification, can be quite conservative. This limits the set of environments for which a safe controller can be obtained. We propose SPEC, a specification-centric simulation metric, which overcomes these limitations by computing the distance using only the trajectories that violate the specification for the system. We show that modifying a reach-avoid specification with SPEC allows us to synthesize a safe controller for a larger set of environments compared to SSM. We also propose a probabilistic method to compute SPEC for a general class of systems. Case studies using simulators for quadrotors and autonomous cars illustrate the advantages of the proposed metric for determining safe environment sets and controllers.

Safety analysis is a necessary component in the design and deployment of autonomous robotic systems. Techniques from robust optimal control theory, such as Hamilton-Jacobi reachability analysis, allow a rigorous formalization of safety as guaranteed constraint satisfaction. Unfortunately, the computational complexity of these tools for general dynamical systems scales poorly with state dimension, making existing tools impractical beyond small problems. Modern reinforcement learning methods have shown promising ability to find approximate yet proficient solutions to optimal control problems in complex and high-dimensional systems, however their application has in practice been restricted to problems with an additive payoff over time, unsuitable for reasoning about safety. In recent work, we introduced a time-discounted modification of the problem of maximizing the minimum payoff over time, central to safety analysis, through a modified dynamic programming equation that induces a contraction mapping. Here, we show how a similar contraction mapping can render reinforcement learning techniques amenable to quantitative safety analysis as tools to approximate the safe set and optimal safety policy. This opens a new avenue of research connecting control-theoretic safety analysis and the reinforcement learning domain. We validate the correctness of our formulation by comparing safety results computed through Q-learning to analytic and numerical solutions, and demonstrate its scalability by learning safe sets and control policies for simulated systems of up to 18 state dimensions using value learning and policy gradient techniques.

We propose a new probabilistic programming language for the design and analysis of perception systems, especially those based on machine learning. Specifically, we consider the problems of training a perception system to handle rare events, testing its performance under different conditions, and debugging failures. We show how a probabilistic programming language can help address these problems by specifying distributions encoding interesting types of inputs and sampling these to generate specialized training and test sets. More generally, such languages can be used for cyber-physical systems and robotics to write environment models, an essential prerequisite to any formal analysis. In this paper, we focus on systems like autonomous cars and robots, whose environment is a scene, a configuration of physical objects and agents. We design a domain-specific language, Scenic, for describing scenarios that are distributions over scenes. As a probabilistic programming language, Scenic allows assigning distributions to features of the scene, as well as declaratively imposing hard and soft constraints over the scene. We develop specialized techniques for sampling from the resulting distribution, taking advantage of the structure provided by Scenic's domain-specific syntax. Finally, we apply Scenic in a case study on a convolutional neural network designed to detect cars in road images, improving its performance beyond that achieved by state-of-the-art synthetic data generation methods.

Recent successes in reinforcement learning have lead to the development of complex controllers for realworld robots. As these robots are deployed in safety-critical applications and interact with humans, it becomes critical to ensure safety in order to avoid causing harm. A first step in this direction is to test the controllers in simulation. To be able to do this, we need to capture what we mean by safety and then efficiently search the space of all behaviors to see if they are safe. In this paper, we present an active-testing framework based on Bayesian Optimization. We specify safety constraints using logic and exploit structure in the problem in order to test the system for adversarial counter examples that violate the safety specifications. These specifications are defined as complex boolean combinations of smooth functions on the trajectories and, unlike reward functions in reinforcement learning, are expressive and impose hard constraints on the system. In our framework, we exploit regularity assumptions on individual functions in form of a Gaussian Process (GP) prior. We combine these into a coherent optimization framework using problem structure. The resulting algorithm is able to provably verify complex safety specifications or alternatively find counter examples. Experimental results show that the proposed method is able to find adversarial examples quickly.

We present a novel framework for augmenting data sets for machine learning based on counterexamples. Counterexamples are misclassified examples that have important properties for retraining and improving the model. Key components of our framework include a \textit{counterexample generator}, which produces data items that are misclassified by the model and error tables, a novel data structure that stores information pertaining to misclassifications. Error tables can be used to explain the model's vulnerabilities and are used to efficiently generate counterexamples for augmentation. We show the efficacy of the proposed framework by comparing it to classical augmentation techniques on a case study of object detection in autonomous driving based on deep neural networks.

We address the problem of diagnosing and repairing specifications for hybrid systems, formalized in signal temporal logic (STL). Our focus is on automatic synthesis of controllers from specifications using model predictive control. We build on recent approaches that reduce the controller synthesis problem to solving one or more mixed integer linear programs (MILPs), where infeasibility of an MILP usually indicates unrealizability of the controller synthesis problem. Given an infeasible STL synthesis problem, we present algorithms that provide feedback on the reasons for unrealizability, and suggestions for making it realizable. Our algorithms are sound and complete relative to the synthesis algorithm, i.e., they provide a diagnosis that makes the synthesis problem infeasible, and always terminate with a non-trivial specification that is feasible using the chosen synthesis method, when such a solution exists. We demonstrate the effectiveness of our approach on controller synthesis for various cyber-physical systems, including an autonomous driving application and an aircraft electric power system.