Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Ghosh, Shromona"'
Autor:
Vin, Eric, Kashiwa, Shun, Rhea, Matthew, Fremont, Daniel J., Kim, Edward, Dreossi, Tommaso, Ghosh, Shromona, Yue, Xiangyu, Sangiovanni-Vincentelli, Alberto L., Seshia, Sanjit A.
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 used for the design and analysis of CPS in a variety of domains, but
Externí odkaz:
http://arxiv.org/abs/2307.03325
Autor:
Fremont, Daniel J., Kim, Edward, Dreossi, Tommaso, Ghosh, Shromona, Yue, Xiangyu, Sangiovanni-Vincentelli, Alberto L., Seshia, Sanjit A.
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 it
Externí odkaz:
http://arxiv.org/abs/2010.06580
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 perception systems, however, are hard to analyze and errors in them can pr
Externí odkaz:
http://arxiv.org/abs/1911.01523
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 networks is known as adversarial input generation. This process depends on
Externí odkaz:
http://arxiv.org/abs/1903.10033
Hamilton-Jacobi-Isaacs (HJI) reachability analysis is a powerful tool for analyzing the safety of autonomous systems. This analysis is computationally intensive and typically performed offline. Online, however, the autonomous system may experience ch
Externí odkaz:
http://arxiv.org/abs/1903.07715
Autor:
Ghosh, Shromona, Bansal, Somil, Sangiovanni-Vincentelli, Alberto, Seshia, Sanjit A., Tomlin, Claire J.
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 environment, a common approach is to synthesize a controller from an
Externí odkaz:
http://arxiv.org/abs/1902.10320
Autor:
Dreossi, Tommaso, Fremont, Daniel J., Ghosh, Shromona, Kim, Edward, Ravanbakhsh, Hadi, Vazquez-Chanlatte, Marcell, Seshia, Sanjit A.
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 particularly seeks to address challenges with applying formal methods to perc
Externí odkaz:
http://arxiv.org/abs/1902.04245
Autor:
Fremont, Daniel J., Dreossi, Tommaso, Ghosh, Shromona, Yue, Xiangyu, Sangiovanni-Vincentelli, Alberto L., Seshia, Sanjit A.
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 problems of training a perception system to handle rare events, testing i
Externí odkaz:
http://arxiv.org/abs/1809.09310
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 be obtained by solving a Hamilton-Jacobi equation. Furthermore, the num
Externí odkaz:
http://arxiv.org/abs/1809.00706
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-shelf components and complex machine-learning techniques. This trend m
Externí odkaz:
http://arxiv.org/abs/1808.07921