235 citations · 356 across the 13 of their papers we have counts for
7 papers · 1 filter
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…