no code implementations • 23 Mar 2024 • Navid Hashemi, Bardh Hoxha, Danil Prokhorov, Georgios Fainekos, Jyotirmoy Deshmukh
We show how this learning problem is similar to training recurrent neural networks (RNNs), where the number of recurrent units is proportional to the temporal horizon of the agent's task objectives.
no code implementations • 13 Sep 2023 • Alexander Bastounis, Alexander N. Gorban, Anders C. Hansen, Desmond J. Higham, Danil Prokhorov, Oliver Sutton, Ivan Y. Tyukin, Qinghua Zhou
We consider classical distribution-agnostic framework and algorithms minimising empirical risks and potentially subjected to some weights regularisation.
no code implementations • 3 Apr 2023 • Mitchell Black, Georgios Fainekos, Bardh Hoxha, Danil Prokhorov, Dimitra Panagou
We propose a novel class of risk-aware control barrier functions (RA-CBFs) for the control of stochastic safety-critical systems.
no code implementations • 7 Mar 2023 • Navid Hashemi, Bardh Hoxha, Tomoya Yamaguchi, Danil Prokhorov, Geogios Fainekos, Jyotirmoy Deshmukh
In this paper, we present a model for the verification of Neural Network (NN) controllers for general STL specifications using a custom neural architecture where we map an STL formula into a feed-forward neural network with ReLU activation.
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 • 30 Dec 2021 • Shakiba Yaghoubi, Georgios Fainekos, Tomoya Yamaguchi, Danil Prokhorov, Bardh Hoxha
Our goal is to design controllers that bound the probability of a system failure in finite-time to a given desired value.
no code implementations • 9 Aug 2021 • Xiaodong Yang, Tom Yamaguchi, Hoang-Dung Tran, Bardh Hoxha, Taylor T Johnson, Danil Prokhorov
Formally verifying the safety and robustness of well-trained DNNs and learning-enabled systems under attacks, model uncertainties, and sensing errors is essential for safe autonomy.
no code implementations • 22 Jun 2021 • Xiaodong Yang, Tomoya Yamaguchi, Hoang-Dung Tran, Bardh Hoxha, Taylor T Johnson, Danil Prokhorov
Besides the computation of reachable sets, our approach is also capable of backtracking to the input domain given an output reachable set.
no code implementations • 2 Aug 2019 • Cumhur Erkan Tuncali, Georgios Fainekos, Danil Prokhorov, Hisahiro Ito, James Kapinski
Additionally, we present three driving scenarios and demonstrate how our requirements-driven testing framework can be used to identify critical system behaviors, which can be used to support the development process.
1 code implementation • 18 Jan 2019 • Fan Yang, Lei Zhang, Sijia Yu, Danil Prokhorov, Xue Mei, Haibin Ling
To demonstrate the superiority and generality of the proposed method, we evaluate the proposed method on five crack datasets and compare it with state-of-the-art crack detection, edge detection, semantic segmentation methods.
no code implementations • 12 Oct 2018 • Ivan Y. Tyukin, Alexander N. Gorban, Stephen Green, Danil Prokhorov
This paper presents a technology for simple and computationally efficient improvements of a generic Artificial Intelligence (AI) system, including Multilayer and Deep Learning neural networks.
no code implementations • 14 Jul 2017 • Tomoki Nishi, Prashant Doshi, Danil Prokhorov
Freeway merging in congested traffic is a significant challenge toward fully automated driving.
no code implementations • 4 Jun 2017 • Tomoki Nishi, Prashant Doshi, Michael R. James, Danil Prokhorov
In many robotic applications, some aspects of the system dynamics can be modeled accurately while others are difficult to obtain or model.
no code implementations • 8 Jul 2016 • Heng Fan, Xue Mei, Danil Prokhorov, Haibin Ling
Context in image is crucial for scene labeling while existing methods only exploit local context generated from a small surrounding area of an image patch or a pixel, by contrast long-range and global contextual information is ignored.
no code implementations • CVPR 2015 • Zhibin Hong, Zhe Chen, Chaohui Wang, Xue Mei, Danil Prokhorov, DaCheng Tao
Variations in the appearance of a tracked object, such as changes in geometry/photometry, camera viewpoint, illumination, or partial occlusion, pose a major challenge to object tracking.