235 citations · 356 across the 13 of their papers we have counts for
18 papers
3D Environment Modeling for Falsification and Beyond with Scenic 3.0
Eric Vin, Shun Kashiwa, Matthew Rhea +7
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…
Scenic: A Language for Scenario Specification and Data Generation
Daniel J. Fremont, Edward Kim, Tommaso Dreossi +4
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…
Counterexample-Guided Synthesis of Perception Models and Control
Shromona Ghosh, Yash Vardhan Pant, Hadi Ravanbakhsh +1
Recent advances in learning-based perception systems have led to drastic improvements in the performance of robotic systems like autonomous vehicles and surgical robots. These perc…
A Formalization of Robustness for Deep Neural Networks
Tommaso Dreossi, Shromona Ghosh, Alberto Sangiovanni-Vincentelli +1
Deep neural networks have been shown to lack robustness to small input perturbations. The process of generating the perturbations that expose the lack of robustness of neural netwo…
Reachability-Based Safety Guarantees using Efficient Initializations
Sylvia L. Herbert, Shromona Ghosh, Somil Bansal +1
Hamilton-Jacobi-Isaacs (HJI) reachability analysis is a powerful tool for analyzing the safety of autonomous systems. This analysis is computationally intensive and typically perfo…
A New Simulation Metric to Determine Safe Environments and Controllers for Systems with Unknown Dynamics
Shromona Ghosh, Somil Bansal, Alberto Sangiovanni-Vincentelli +2
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…
VERIFAI: A Toolkit for the Design and Analysis of Artificial Intelligence-Based Systems
Tommaso Dreossi, Daniel J. Fremont, Shromona Ghosh +4
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 particu…
A Minimum Discounted Reward Hamilton-Jacobi Formulation for Computing Reachable Sets
Anayo K. Akametalu, Shromona Ghosh, Jaime F. Fisac +1
We propose a novel formulation for approximating reachable sets through a minimum discounted reward optimal control problem. The formulation yields a continuous solution that can b…
Scenic: A Language for Scenario Specification and Scene Generation
Daniel J. Fremont, Tommaso Dreossi, Shromona Ghosh +3
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 pro…
SOTER: A Runtime Assurance Framework for Programming Safe Robotics Systems
Ankush Desai, Shromona Ghosh, Sanjit A. Seshia +2
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-…
Counterexample-Guided Data Augmentation
Tommaso Dreossi, Shromona Ghosh, Xiangyu Yue +3
We present a novel framework for augmenting data sets for machine learning based on counterexamples. Counterexamples are misclassified examples that have important properties for r…
Context-Specific Validation of Data-Driven Models
Somil Bansal, Shromona Ghosh, Alberto Sangiovanni-Vincentelli +2
With an increasing use of data-driven models to control robotic systems, it has become important to develop a methodology for validating such models before they can be deployed to…
Verifying Controllers Against Adversarial Examples with Bayesian Optimization
Shromona Ghosh, Felix Berkenkamp, Gireeja Ranade +2
Recent successes in reinforcement learning have lead to the development of complex controllers for real-world robots. As these robots are deployed in safety-critical applications a…
Time Series Learning using Monotonic Logical Properties
Marcell Vazquez-Chanlatte, Shromona Ghosh, Jyotirmoy V. Deshmukh +2
Cyber-physical systems of today are generating large volumes of time-series data. As manual inspection of such data is not tractable, the need for learning methods to help discover…
Systematic Testing of Convolutional Neural Networks for Autonomous Driving
Tommaso Dreossi, Shromona Ghosh, Alberto Sangiovanni-Vincentelli +1
We present a framework to systematically analyze convolutional neural networks (CNNs) used in classification of cars in autonomous vehicles. Our analysis procedure comprises an ima…
Tunable Reactive Synthesis for Lipschitz-Bounded Systems with Temporal Logic Specifications
Marcell Vazquez-Chanlatte, Shromona Ghosh, Vasumathi Raman +2
We address the problem of synthesizing reactive controllers for cyber-physical systems subject to Signal Temporal Logic (STL) specifications in the presence of adversarial inputs.…
Diagnosis and Repair for Synthesis from Signal Temporal Logic Specifications
Shromona Ghosh, Dorsa Sadigh, Pierluigi Nuzzo +5
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 o…
Robust Online Monitoring of Signal Temporal Logic
Jyotirmoy V. Deshmukh, Alexandre Donzé, Shromona Ghosh +3
Signal Temporal Logic (STL) is a formalism used to rigorously specify requirements of cyberphysical systems (CPS), i.e., systems mixing digital or discrete components in interactio…