no code implementations • 12 Feb 2024 • Yiqi Zhao, Xinyi Yu, Jyotirmoy V. Deshmukh, Lars Lindemann
Motivated by the advances in conformal prediction (CP), we propose conformal predictive programming (CPP), an approach to solve chance constrained optimization (CCO) problems, i. e., optimization problems with nonlinear constraint functions affected by arbitrary random parameters.
1 code implementation • 16 Nov 2023 • Yiqi Zhao, Bardh Hoxha, Georgios Fainekos, Jyotirmoy V. Deshmukh, Lars Lindemann
To address these challenges, we assume to know an upper bound on the statistical distance (in terms of an f-divergence) between the distributions at deployment and design time, and we utilize techniques based on robust conformal prediction.
no code implementations • 9 Nov 2023 • Aniruddh G. Puranic, Jyotirmoy V. Deshmukh, Stefanos Nikolaidis
Apprenticeship learning crucially depends on effectively learning rewards, and hence control policies from user demonstrations.
no code implementations • 17 Sep 2023 • Navid Hashemi, Xin Qin, Lars Lindemann, Jyotirmoy V. Deshmukh
We consider data-driven reachability analysis of discrete-time stochastic dynamical systems using conformal inference.
no code implementations • 12 Aug 2023 • Xin Qin, Navid Hashemi, Lars Lindemann, Jyotirmoy V. Deshmukh
Ultimately, conformance can capture distance between design models and their real implementations and thus aid in robust system design.
no code implementations • 5 Apr 2023 • Navid Hashemi, Justin Ruths, Jyotirmoy V. Deshmukh
The problem addressed by this paper is the following: Suppose we obtain an optimal trajectory by solving a control problem in the training environment, how do we ensure that the real-world system trajectory tracks this optimal trajectory with minimal amount of error in a deployment environment.
no code implementations • 5 Dec 2022 • Sheryl Paul, Jyotirmoy V. Deshmukh
In this paper, we consider the problem of path finding for a set of homogeneous and autonomous agents navigating a previously unknown stochastic environment.
no code implementations • 3 Nov 2022 • Lars Lindemann, Xin Qin, Jyotirmoy V. Deshmukh, George J. Pappas
The second algorithm constructs prediction regions for future system states first, and uses these to obtain a prediction region for the satisfaction measure.
no code implementations • 14 Oct 2022 • Navid Hashemi, Xin Qin, Jyotirmoy V. Deshmukh, Georgios Fainekos, Bardh Hoxha, Danil Prokhorov, Tomoya Yamaguchi
In this paper, we consider the problem of synthesizing a controller in the presence of uncertainty such that the resulting closed-loop system satisfies certain hard constraints while optimizing certain (soft) performance objectives.
no code implementations • 1 Jul 2022 • Sara Mohammadinejad, Jesse Thomason, Jyotirmoy V. Deshmukh
In this work, we propose DIALOGUESTL, an interactive approach for learning correct and concise STL formulas from (often) ambiguous NL descriptions.
1 code implementation • 29 Jun 2022 • Mohammad Hekmatnejad, Bardh Hoxha, Jyotirmoy V. Deshmukh, Yezhou Yang, Georgios Fainekos
Automated vehicles (AV) heavily depend on robust perception systems.
no code implementations • 12 Apr 2022 • Aniruddh G. Puranic, Jyotirmoy V. Deshmukh, Stefanos Nikolaidis
In the learning from demonstration (LfD) paradigm, understanding and evaluating the demonstrated behaviors plays a critical role in extracting control policies for robots.
no code implementations • 4 Feb 2022 • Anand Balakrishnan, Stefan Jakšić, Edgar A. Aguilar, Dejan Ničković, Jyotirmoy V. Deshmukh
There are several examples of the use of formal languages such as temporal logics and automata to specify high-level task specifications for robots (in lieu of Markovian rewards).
no code implementations • 29 Jul 2021 • Gaurav Gupta, Chenzhong Yin, Jyotirmoy V. Deshmukh, Paul Bogdan
Reinforcement learning (RL) is a technique to learn the control policy for an agent that interacts with a stochastic environment.
no code implementations • 15 Feb 2021 • Aniruddh G. Puranic, Jyotirmoy V. Deshmukh, Stefanos Nikolaidis
Learning-from-demonstrations is an emerging paradigm to obtain effective robot control policies for complex tasks via reinforcement learning without the need to explicitly design reward functions.
no code implementations • 10 Nov 2020 • Parv Kapoor, Anand Balakrishnan, Jyotirmoy V. Deshmukh
In this paper, we propose expressing desired high-level robot behavior using a formal specification language known as Signal Temporal Logic (STL) as an alternative to reward/cost functions.
no code implementations • 20 Jul 2020 • Sara Mohammadinejad, Brandon Paulsen, Chao Wang, Jyotirmoy V. Deshmukh
As the memory footprint and energy consumption of such components become a bottleneck, there is interest in compressing and optimizing such networks using a range of heuristic techniques.
no code implementations • 18 May 2020 • Sara Mohammadinejad, Jyotirmoy V. Deshmukh, Aniruddh G. Puranic
We assume that the correctness of each component can be specified as a requirement satisfied by the output signals produced by the component, and that such an output guarantee is expressed in a real-time temporal logic such as Signal Temporal Logic (STL).
no code implementations • 24 Jul 2019 • Sara Mohammadinejad, Jyotirmoy V. Deshmukh, Aniruddh G. Puranic, Marcell Vazquez-Chanlatte, Alexandre Donzé
Cyber-physical system applications such as autonomous vehicles, wearable devices, and avionic systems generate a large volume of time-series data.
no code implementations • 11 Apr 2018 • Cumhur Erkan Tuncali, James Kapinski, Hisahiro Ito, Jyotirmoy V. Deshmukh
We present a simulation-based approach for generating barrier certificate functions for safety verification of cyber-physical systems (CPS) that contain neural network-based controllers.
no code implementations • 24 Feb 2018 • Marcell Vazquez-Chanlatte, Shromona Ghosh, Jyotirmoy V. Deshmukh, Alberto Sangiovanni-Vincentelli, Sanjit A. Seshia
Cyber-physical systems of today are generating large volumes of time-series data.
no code implementations • 22 Dec 2016 • Marcell Vazquez-Chanlatte, Jyotirmoy V. Deshmukh, Xiaoqing Jin, Sanjit A. Seshia
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.