Alberto Sangiovanni Vincentelli

• Dr. of Engineering
• Chair at University of California, Berkeley

Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly reduced attack success rate, but their prediction accuracy on clean data still lags behind a clean model by a la...

Deriving system-level specifications from component specifications usually involves the elimination of variables that are not part of the interface of the top-level system. This paper presents algorithms for eliminating variables from formulas by computing refinements or relaxations of these formulas in a context. We discuss a connection between th...

Contract-based design is a method to facilitate modular system design. While there has been substantial progress on the theory of contracts, there has been less progress on scalable algorithms for the algebraic operations in this theory. In this paper, we present: 1) principles to implement a contract-based design tool at scale and 2) Pacti, a tool...

We propose a context-sensitive grammar for the systematic exploration of the design space of the topology of 3D robots, particularly unmanned aerial vehicles. It defines production rules for adding components to an incomplete design topology modeled over a 3D grid. The rules are local. The grammar is simple, yet capable of modeling most existing UA...

Several machine learning (ML) applications are characterized by searching for an optimal solution to a complex task. The search space for this optimal solution is often very large, so large in fact that this optimal solution is often not computable. Part of the problem is that many candidate solutions found via ML are actually infeasible and have t...

We present a methodology for scalable exploration of cyber-physical system architectures. We propose a mathematical formulation of the architecture exploration problem as an optimized mapping problem that includes joint selection of system topologies and components taken from pre-defined libraries. Using a graph-based representation of an architect...

de Alfaro and Henzinger’s interface automata brought renewed vigor to the tasks of specifying software formally and reasoning about systems compositionally. The key ingredients to this approach were the separation of concerns between environment and implementation, a light-weight behavioral interface that enabled more comprehensive compatibility ch...

We address the problem of modeling, refining, and repairing formal specifications for robotic missions using assume-guarantee contracts. We show how to model mission specifications at various levels of abstraction and implement them using a library of pre-implemented specifications. Suppose the specification cannot be met using components from the...

The capability of a reinforcement learning (RL) agent heavily depends on the diversity of the learning scenarios generated by the environment. Generation of diverse realistic scenarios is challenging for real-time strategy (RTS) environments. The RTS environments are characterized by intelligent entities/non-RL agents cooperating and competing with...

Background: At the onset of a pandemic, such as COVID-19, data with proper labeling/attributes corresponding to the new disease might be unavailable or sparse. Machine Learning (ML) models trained with the available data, which is limited in quantity and poor in diversity, will often be biased and inaccurate. At the same time, ML algorithms designe...

Contract theories have been proposed to formally support distributed and decentralized system design while ensuring safe system integration. We propose hypercontracts, a general model with a richer structure for its underlying model of components, subsuming simulation preorders. While general, the new model provides a richer algebra for its notions...

We provide a new perspective on using formal methods to model specifications and synthesize implementations for the design of biological circuits. In synthetic biology, design objectives are rarely described formally. We present an assume-guarantee contract framework to describe biological circuit design objectives as formal specifications. In our...

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 sho...

Simulation-based testing of autonomous vehicles (AVs) has become an essential complement to road testing to ensure safety. Consequently, substantial research has focused on searching for failure scenarios in simulation. However, a fundamental question remains: are AV failure scenarios identified in simulation meaningful in reality, i.e., are they r...

We present a general framework for the control of a direct current (DC) microgrid with star topology (a common DC bus) consisting of renewable sources of energy, loads, and storage devices connected via step-up and step-down DC/DC converters. The control objective is guaranteeing voltage stability in the DC microgrid while delivering power to the l...

We consider the problem of detecting OoD(Out-of-Distribution) input data when using deep neural networks, and we propose a simple yet effective way to improve the robustness of several popular OoD detection methods against label shift. Our work is motivated by the observation that most existing OoD detection algorithms consider all training/test da...

We investigate the role of explainable Artificial Intelligence (XAI) for building trust in data-driven fault detection and diagnosis (FDD). We examine use cases for XAI-FDD on a building in Singapore that has six chillers.

\textbf{Background:}$ At the onset of a pandemic, such as COVID-19, data with proper labeling/attributes corresponding to the new disease might be unavailable or sparse. Machine Learning (ML) models trained with the available data, which is limited in quantity and poor in diversity, will often be biased and inaccurate. At the same time, ML algorith...

The difficulty in acquiring fault label data is a major obstacle to the application of data-driven fault isolation in DC microgrids. To remove this barrier, this paper introduces an approach of generating synthetic data with the line currents measured during normal operation as the substitute for fault label data in training an ensemble model, whic...

This paper introduces the a framework that simplifies the process of designing and describing autonomous vehicle platooning manoeuvres which implements four design principles: Standardisation, Encapsulation, Abstraction, and Decoupling (SEAD). Although a large body of research has been formulating platooning manoeuvres, it is still challenging to d...

Test for Reliability is a test flow where an Integrated Circuit (IC) device is continuously stressed under several corner conditions that can be dynamically adapted based on the real-time observation of the critical signals of the device during the evolution of the test. We present our approach for a successful Test-for-Reliability flow, going beyo...

Industry 4.0 is changing data collection, storage, and analysis in industrial processes fundamentally, enabling novel applications such as flexible manufacturing of highly customized products. However, real-time control of these processes has not yet realized its full potential in using the collected data to drive further development. Indeed, typic...

Contracts (or interface) theories have been proposed to formally support distributed and decentralized system design while ensuring safe system integration. Over the last decades, a number of formalisms were proposed, sometimes very different in their form and algebra. This motivated the quest for a unification by some authors, e.g., specifications...

This paper introduces the SEAD framework that simplifies the process of designing and describing autonomous vehicle platooning manoeuvres. Although a large body of research has been formulating platooning manoeuvres, it is still challenging to design, describe, read, and understand them. This difficulty largely arises from missing formalisation. To...

Microscopic agent-based traffic simulation is an important tool for the efficient and safe resolution of various traffic challenges accompanying the introduction of autonomous vehicles on the roads. Both the variety of questions that can be asked and the quality of answers provided by simulations, however, depend on the underlying models. In mixed...

Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of domain shift, the learned knowledge of the well-trained DNNs cannot be well generalized to new domains or datasets that have few labels. Unsupervised domain adaptation (UD...

Safely interacting with humans is a significant challenge for autonomous driving. The performance of this interaction depends on machine learning-based modules of an autopilot, such as perception, behavior prediction, and planning. These modules require training datasets with high-quality labels and a diverse range of realistic dynamic behaviors. C...

Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of domain shift, the learned knowledge of the well-trained DNNs cannot be well generalized to new domains or datasets that have few labels. Unsupervised domain adaptation (UD...

Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained o...

We propose a new probabilistic programming language for the design and analysis of cyber-physical systems, especially those based on machine learning. Specifically, we consider the problems of training a system to be robust to rare events, testing its performance under different conditions, and debugging failures. We show how a probabilistic progra...

Seeking the largest solution to an expression of the form A x <= B is a common task in several domains of engineering and computer science. This largest solution is commonly called quotient. Across domains, the meanings of the binary operation and the preorder are quite different, yet the syntax for computing the largest solution is remarkably simi...

Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks. However, in many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data. To cope with limited labeled training data, many have attempted to directly apply models trained o...

The increasing penetration of wearable and implantable devices necessitates energy-efficient and robust ways of connecting them to each other and to the cloud. However, the wireless channel around the human body poses unique challenges such as a high and variable path-loss caused by frequent changes in the relative node positions as well as the sur...

Accurate localization from Cyber-Physical Systems (CPS) is a critical enabling technology for context-aware applications and control. As localization plays an increasingly safety-critical role, location systems must be able to identify and eliminate faulty measurements to prevent dangerously inaccurate localization. In this article, we consider the...

Industry 4.0 is changing fundamentally data collection, its storage and analysis in industrial processes, enabling novel application such as flexible manufacturing of highly customized products. Real-time control of these processes, however, has not yet realized its full potential in using the collected data to drive further development. Indeed, ty...

This paper describes a component-based concurrent model of computation for reactive systems. The components in this model, featuring ports and hierarchy, are called reactors. The model leverages a semantic notion of time, an event scheduler, and a synchronous-reactive style of communication to achieve determinism. Reactors enable a programming mode...

We address the problem of synthesizing safety-critical embedded and cyber-physical system architectures to minimize a cost function while guaranteeing the desired reliability. We represent a system architecture as a configurable graph in which both the nodes (components) and edges (interconnections) may fail. We then propose a compact analytical fo...

Industry 4.0 is changing fundamentally the way data is collected, stored and analyzed in industrial processes, enabling novel application such as flexible manufacturing of highly customized products. Real-time control of these processes, however, has not yet realized its full potential in using the data collected to drive further development. We be...

Contract models have been proposed to promote and facilitate reuse and distributed development. In this paper, we cast contract models into a coherent formalism used to derive general results about the properties of their operators. We study several extensions of the basic model, including the distinction between weak and strong assumptions and max...

The Monte Carlo dropout method has proved to be a scalable and easy-to-use approach for estimating the uncertainty of deep neural network predictions. This approach was recently applied to Fault Detection and Di-agnosis (FDD) applications to improve the classification performance on incipient faults. In this paper, we propose a novel approach of au...

We propose to harness the potential of simulation for the semantic segmentation of real-world self-driving scenes in a domain generalization fashion. The segmentation network is trained without any data of target domains and tested on the unseen target domains. To this end, we propose a new approach of domain randomization and pyramid consistency t...

Printed Circuit Board (PCB) design tools are critical in helping users build non-trivial electronics devices. While recent work recognizes deficiencies with current tools and explores novel methods, little has been done to understand modern designers and their needs. To gain better insight into their practices, we interview fifteen electronics desi...

The article is a reflection onmy journey during the development of the EDA field, from its early days to its explosive growth and present maturity. The two special issues of the Solid State Circuit Society Magazine "Corsi e Ricorsi: Alberto Sangiovanni Vincentelli and the Evolution of EDA", published in 2010 [1,2], contain a set of papers that pinp...

We present an assume-guarantee contract framework for cyber-physical system design under probabilistic requirements. Given a stochastic linear system and a set of requirements captured by bounded Stochastic Signal Temporal Logic (StSTL) contracts, we propose algorithms to check contract compatibility, consistency, and refinement, and generate a seq...

Synthetic data has proved increasingly useful in both training and testing machine learning models such as neural networks. The major problem in synthetic data generation is producing meaningful data that is not simply random but reflects properties of real-world data or covers particular cases of interest. In this paper, we show how a probabilisti...

The design of cyber-physical systems (CPSs) requires methods and tools that can efficiently reason about the interaction between discrete models, e.g., representing the behaviors of "cyber" components, and continuous models of physical processes. Boolean methods such as satisfiability (SAT) solving are successful in tackling large combinatorial sea...

A new mobile healthcare system for neuro-cognitive function monitoring and treatment is presented. The architecture of the system features sensors to measure the brain potential, localized data analysis and filtering, and in-cloud distribution to specialized medical personnel. As such, it presents tradeoffs typical of other cyber-physical systems,...

We propose the notions of heterogeneous refinement and vertical contracts as additions for any contract framework to provide full methodological support for multi-view and multi-layer system design with heterogeneous models. We rethink the relation of contract refinement in the context of layered design and discuss how it can be extended, via heter...

This paper studies the co-design optimization approach to determine how to optimally adapt automatic control of an intelligent electric vehicle to driving styles. A cyber-physical system (CPS) based framework is proposed for co-design optimization of the plant and controller parameters for an automated electric vehicle, in view of vehicle's dynamic...

3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can generate depth information of the environment. However, creating large 3D LiDAR point cloud datasets with point-level labels requires a significant amount of manual annotation. This jeopardizes the efficient development of supervised deep learning algorit...

3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can generate depth information of the environment. However, creating large 3D LiDAR point cloud datasets with point-level labels requires a significant amount of manual annotation. This jeopardizes the efficient development of supervised deep learning algorit...

Internet-of-Things and machine learning promise a new era for healthcare. The emergence of transformative technologies, such as Implantable and Wearable Medical Devices (IWMDs), has enabled collection and analysis of physiological signals from anyone anywhere anytime. Machine learning allows us to unearth patterns in these signals and make healthca...

Recently, contract-based design has been proposed as an “orthogonal” approach that complements system design methodologies proposed so far to cope with the complexity of system design. Contract-based design provides a rigorous scaffolding for verification, analysis, abstraction/refinement, and even synthesis. Several results have been obtained in t...

Vehicles have mutated from mechanical systems into cyberphysical systems featuring a large number of electronic control units (ECUs), sensors, and actuators. The wiring harnesses used for the transmission of data and power delivery for these components may have up to 4,000 parts, weigh as much as 40 kg, and contain up to 4 km of wiring. The amount...

The Internet of Things (IoT) refers to the interconnection of everyday objects endowed with sensing, processing, communication and energy management capabilities [item 1) in the Appendix] (the “IoT nodes”). Being at the beginning of its “S curve” in terms of stage of adoption [item 2) in the Appendix] (see “innovators” in Fig. 1 ), the IoT promise...

We address the design space exploration of wireless body area networks for wearable and implantable technologies, a task that is increasingly challenging as the number and variety of devices per person grow. Our method efficiently decomposes the problem into smaller subproblems by coordinating specialized analysis and optimization techniques. We le...

The contract-based design formalism supports compositional design and verification, and generalizes many other languages where components are defined in terms of their assumptions and guarantees. Most languages and tools for contract-based design provide constructs to define, instantiate, and connect contracts, but fall short in capturing families...

Small, energy-efficient sensor and actuator interfaces, as enabled by nanotechnologies, are revolutionizing the way we interact with computers and the physical world, and are ultimately leading to the realization of sophisticated cyber-physical systems (CPSs). By tightly combining computing, networking, and control (the “cyber” part of the system)...

We present a mathematical programming-based method for model predictive control of cyber-physical systems subject to signal temporal logic (STL) specifications. We describe the use of STL to specify a wide range of properties of these systems, including safety, response and bounded liveness. For synthesis, we encode STL specifications as mixed inte...

We propose a novel approach that integrates wireless, non-invasive devices with fast, real-time algorithms for large data analysis and biofeedback reaction, to discern the voluntariness of human movement through direct sensing of brain potentials combined with muscular action signal monitoring. The system has been tested in real situations.

We address the problem of diagnosing and repairing specifications for hybrid systems formalized in signal temporal logic (STL). Our focus is on the setting of automatic synthesis of controllers in a model predictive control (MPC) framework. We build on recent approaches that reduce the controller synthesis problem to solving one or more mixed integ...

The term intelligent or smart building refers to the next generation of buildings that provide new levels of comfort to the occupants with minimum possible energy consumption. They not only follow commands but also proactively learn from occupants' behavior and adapt their operation based on the indoor and outdoor conditions. These buildings are no...

Demand Response (DR) is considered a promising approach to cope with the increasing variability in power grids due to the penetration of renewable energy sources. However, it still remains a challenge to manage the aggregation of a large number of heterogeneous loads to achieve a desired response, especially at a fast time scale. In this paper, we...

As a complex cyber-physical system, smart grid has been going through major upgrades in three verticals: 1) new hardware such as solar panels, wind generation turbines, and plug-in electric vehicles, 2) new sensing devices such as smart meters and smart thermostats, and 3) new communication and computation infrastructure such as the broadband two-w...

In this paper, we address both of security and safety requirements and solve security-aware design problems for the Controller Area Network (CAN) protocol and Time Division Multiple Access (TDMA) based protocols. To provide insights and guidelines for other similar security problems with limited resources and strict timing constraints, we propose a...

Aircrafts, trains, cars, plants, distributed telecommunication military or health care systems,and more, involve systems design as a critical step. Complexity has caused system design times and coststo go severely over budget so as to threaten the health of entire industrial sectors. Heuristic methods andstandard practices do not seem to scale with...

Recently, contract based design has been proposed as an ”orthogonal” approach that can beapplied to all methodologies proposed so far to cope with the complexity of system design. Contract baseddesign provides a rigorous scaffolding for verification, analysis and abstraction/refinement. Companionreport RR-8759 proposes a unified treatment of the to...

Aircraft Electric Power Systems (EPS) route power from generators to vital avionics loads by configuring a set of electronic control switches denoted as contactors. The external loads applied to an EPS, power requirement of the system, electrical component failure events, and the dynamics of the system are inherently uncertain. In this paper, we ad...

We present an innovative wireless wearable, low power, noninvasive neuroprosthetic system that is geared towards detecting and preventing falls. The system allows continuous monitoring of EEG/EMG, detecting in particular pre-motor potentials to prevent falls of elder and motor-impaired patients by introducing a feedback action to stabilize gait. A...

In this paper, we present the essential features of CPS Systems of Systems (SoS) and we develop a conceptual, rigorous model for such systems that can support the development of analysis and synthesis tools. We also address issues related to safety critical and secure applications and we outline how to cope with failures of SoS.

Security has become a critical issue for automotive electronic systems. To protect against attacks, security mechanisms have to be applied, but the overhead of those mechanisms may impede system performance and cause violations of design constraints. To remedy this problem, we proposed an integrated mixed integer linear programming (MILP) formulati...

The paper describes the architecture of a non-invasive, wireless system for fall prevention. The system includes: i) a wearable electroencephalography (EEG) and electromyography (EMG) measurement subsystem that detects the occurrence of unintentional limb movements as sign of a potential fall, and ii) a computing subsystem that classifies EEG-EMG s...

We address the problem of detecting and mitigating the effect of malicious attacks to the sensors of a linear dynamical system. We develop a novel, efficient algorithm that uses a Satisfiability-Modulo-Theory approach to isolate the compromised sensors and estimate the system state despite the presence of the attack, thus harnessing the intrinsic c...