Search Results for author:
Found 54 papers, 13 papers with code
Privacy Preserving Mechanisms for Coordinating Airspace Usage in Advanced Air Mobility
To ensure the cost information of AAM vehicles remains private, we introduce a novel mechanism that allocates each vehicle a budget of "air-credits" and anonymously charges prices for traversing the edges of the time-extended graph.
Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
Goal-conditioned reinforcement learning is a powerful way to control an AI agent's behavior at runtime.
SimpleStrat: Diversifying Language Model Generation with Stratification
As computing probability per response/solution for proprietary models is infeasible, we measure recall on ground truth solutions.
Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languages
Unsurprisingly, however, models struggle to compose syntactically valid programs in programming languages unrepresented in pre-training, referred to as very low-resource Programming Languages (VLPLs).
ScenicNL: Generating Probabilistic Scenario Programs from Natural Language
Reports normally contain uncertainty about the exact details of the incidents which we represent through a Probabilistic Programming Language (PPL), Scenic.
LTL-Constrained Policy Optimization with Cycle Experience Replay
In this work, we present Cycle Experience Replay (CyclER), a reward-shaping approach to this problem that allows continuous state and action spaces and the use of function approximations.
$L^*LM$: Learning Automata from Examples using Natural Language Oracles
Due to the expressivity of natural language, we observe a significant improvement in the data efficiency of learning DFAs from expert demonstrations.
An Eager Satisfiability Modulo Theories Solver for Algebraic Datatypes
Specifically, our solver reduces ADT queries to a simpler logical theory, uninterpreted functions (UF), and then uses an existing solver on the reduced query.
Learning Formal Specifications from Membership and Preference Queries
Active learning is a well-studied approach to learning formal specifications, such as automata.
Specification-Guided Data Aggregation for Semantically Aware Imitation Learning
Advancements in simulation and formal methods-guided environment sampling have enabled the rigorous evaluation of machine learning models in a number of safety-critical scenarios, such as autonomous driving.
A Grammar for the Representation of Unmanned Aerial Vehicles with 3D Topologies
It can be thought of as a building block for any design exploration and optimization algorithm.
Demonstration Informed Specification Search
This paper considers the problem of learning temporal task specifications, e. g. automata and temporal logic, from expert demonstrations.
A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulation
Hence, it is important that these prediction models are extensively tested in various test scenarios involving interactive behaviors prior to deployment.
Addressing the IEEE AV Test Challenge with Scenic and VerifAI
Sampling from an abstract scenario yields many different concrete scenarios which can be run as test cases for the AV.
Synthesizing Pareto-Optimal Interpretations for Black-Box Models
For a given black-box, our approach yields a set of Pareto-optimal interpretations with respect to the correctness and explainability measures.
Satisfiability and Synthesis Modulo Oracles
As a necessary component of this framework, we also formalize the problem of satisfiability modulo theories and oracles, and present an algorithm for solving this problem.
Parallel and Multi-Objective Falsification with Scenic and VerifAI
Falsification has emerged as an important tool for simulation-based verification of autonomous systems.
Scenic4RL: Programmatic Modeling and Generation of Reinforcement Learning Environments
To showcase the benefits, we interfaced SCENIC to an existing RTS environment Google Research Football(GRF) simulator and introduced a benchmark consisting of 32 realistic scenarios, encoded in SCENIC, to train RL agents and testing their generalization capabilities.
Scenic: A Language for Scenario Specification and Data Generation
We design a domain-specific language, Scenic, for describing scenarios that are distributions over scenes and the behaviors of their agents over time.
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.
SOTER on ROS: A Run-Time Assurance Framework on the Robot Operating System
We present an implementation of SOTER, a run-time assurance framework for building safe distributed mobile robotic (DMR) systems, on top of the Robot Operating System (ROS).
Gradient Descent over Metagrammars for Syntax-Guided Synthesis
The performance of a syntax-guided synthesis algorithm is highly dependent on the provision of a good syntactic template, or grammar.
Learning Branching Heuristics for Propositional Model Counting
In addition to step count improvements, Neuro# can also achieve orders of magnitude wall-clock speedups over the vanilla solver on larger instances in some problem families, despite the runtime overhead of querying the model.
Enforcing Almost-Sure Reachability in POMDPs
Partially-Observable Markov Decision Processes (POMDPs) are a well-known stochastic model for sequential decision making under limited information.
Formal Analysis and Redesign of a Neural Network-Based Aircraft Taxiing System with VerifAI
We demonstrate a unified approach to rigorous design of safety-critical autonomous systems using the VerifAI toolkit for formal analysis of AI-based systems.
Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World
We present a new approach to automated scenario-based testing of the safety of autonomous vehicles, especially those using advanced artificial intelligence-based components, spanning both simulation-based evaluation as well as testing in the real world.
Modularity in Query-Based Concept Learning
We define and study the problem of modular concept learning, that is, learning a concept that is a cross product of component concepts.
Counterexample-Guided Synthesis of Perception Models and Control
The framework uses a falsifier to find counterexamples, or traces of the systems that violate a safety property, to extract information that enables efficient modeling of the perception modules and errors in it.
On the Utility of Learning about Humans for Human-AI Coordination
While we would like agents that can coordinate with humans, current algorithms such as self-play and population-based training create agents that can coordinate with themselves.
Maximum Causal Entropy Specification Inference from Demonstrations
In many settings (e. g., robotics) demonstrations provide a natural way to specify tasks; however, most methods for learning from demonstrations either do not provide guarantees that the artifacts learned for the tasks, such as rewards or policies, can be safely composed and/or do not explicitly capture history dependencies.
Learning Heuristics for Automated Reasoning through Reinforcement Learning
We demonstrate how to learn efficient heuristics for automated reasoning algorithms through deep reinforcement learning.
A Formalization of Robustness for Deep Neural Networks
The process of generating the perturbations that expose the lack of robustness of neural networks is known as adversarial input generation.
A Model Counter's Guide to Probabilistic Systems
In this paper, we systematize the modeling of probabilistic systems for the purpose of analyzing them with model counting techniques.
VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based Systems
We present VERIFAI, a software toolkit for the formal design and analysis of systems that include artificial intelligence (AI) and machine learning (ML) components.
Scenic: A Language for Scenario Specification and Scene Generation
We propose a new probabilistic programming language for the design and analysis of perception systems, especially those based on machine learning.
Cloud-based Quadratic Optimization with Partially Homomorphic Encryption
The development of large-scale distributed control systems has led to the outsourcing of costly computations to cloud-computing platforms, as well as to concerns about privacy of the collected sensitive data.
Optimization and Control Cryptography and Security Systems and Control
SOTER: A Runtime Assurance Framework for Programming Safe Robotics Systems
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.
Learning Heuristics for Quantified Boolean Formulas through Deep Reinforcement Learning
We demonstrate how to learn efficient heuristics for automated reasoning algorithms for quantified Boolean formulas through deep reinforcement learning.
Counterexample-Guided Data Augmentation
We present a novel framework for augmenting data sets for machine learning based on counterexamples.
Semantic Adversarial Deep Learning
However, existing approaches to generating adversarial examples and devising robust ML algorithms mostly ignore the semantics and context of the overall system containing the ML component.
A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Driving
The framework supports data collection from both auto-driving scenes and user-configured scenes.
Unsupervised Domain Adaptation: from Simulation Engine to the RealWorld
To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled target domain.
Time Series Learning using Monotonic Logical Properties
Cyber-physical systems of today are generating large volumes of time-series data.
Context-Specific Validation of Data-Driven Models
We propose a context-specific validation framework to quantify the quality of a learned model based on a distance measure between the closed-loop actual system and the learned model.
Learning Task Specifications from Demonstrations
In this paper, we formulate the specification inference task as a maximum a posteriori (MAP) probability inference problem, apply the principle of maximum entropy to derive an analytic demonstration likelihood model and give an efficient approach to search for the most likely specification in a large candidate pool of specifications.
Systematic Testing of Convolutional Neural Networks for Autonomous Driving
We present a framework to systematically analyze convolutional neural networks (CNNs) used in classification of cars in autonomous vehicles.
Compositional Falsification of Cyber-Physical Systems with Machine Learning Components
This raises the question: can the output from learning components can lead to a failure of the entire CPS?
Logic-based Clustering and Learning for Time-Series Data
To effectively analyze and design cyberphysical systems (CPS), designers today have to combat the data deluge problem, i. e., the burden of processing intractably large amounts of data produced by complex models and experiments.
Towards Verified Artificial Intelligence
Verified artificial intelligence (AI) is the goal of designing AI-based systems that that have strong, ideally provable, assurances of correctness with respect to mathematically-specified requirements.
Constrained Sampling and Counting: Universal Hashing Meets SAT Solving
Constrained sampling and counting are two fundamental problems in artificial intelligence with a diverse range of applications, spanning probabilistic reasoning and planning to constrained-random verification.
A Theory of Formal Synthesis via Inductive Learning
In this paper, we present a theoretical framework for formal inductive synthesis.
Are There Good Mistakes? A Theoretical Analysis of CEGIS
The history bounded counterexample used in any iteration of CEGIS is bounded by the examples used in previous iterations of inductive synthesis.
Distribution-Aware Sampling and Weighted Model Counting for SAT
We present a novel approach that works with a black-box oracle for weights of assignments and requires only an {\NP}-oracle (in practice, a SAT-solver) to solve both the counting and sampling problems.
Robust Subspace System Identification via Weighted Nuclear Norm Optimization
As in robust PCA, it can be problematic to find a suitable regularization parameter.
