Search Results for author: Radu Calinescu

Found 11 papers, 3 papers with code

Out-of-distribution Object Detection through Bayesian Uncertainty Estimation

no code implementations29 Oct 2023 Tianhao Zhang, Shenglin Wang, Nidhal Bouaynaya, Radu Calinescu, Lyudmila Mihaylova

The superior performance of object detectors is often established under the condition that the test samples are in the same distribution as the training data.

Object object-detection +1

Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction

1 code implementation18 Aug 2023 Daniel Bethell, Simos Gerasimou, Radu Calinescu

Deploying deep learning models in safety-critical applications remains a very challenging task, mandating the provision of assurances for the dependable operation of these models.

Conformal Prediction Decision Making +1

Bayesian Learning for the Robust Verification of Autonomous Robots

1 code implementation15 Mar 2023 Xingyu Zhao, Simos Gerasimou, Radu Calinescu, Calum Imrie, Valentin Robu, David Flynn

Autonomous robots used in infrastructure inspection, space exploration and other critical missions operate in highly dynamic environments.

Closed-loop Analysis of Vision-based Autonomous Systems: A Case Study

no code implementations6 Feb 2023 Corina S. Pasareanu, Ravi Mangal, Divya Gopinath, Sinem Getir Yaman, Calum Imrie, Radu Calinescu, Huafeng Yu

We address the above challenges by replacing the camera and the network with a compact probabilistic abstraction built from the confusion matrices computed for the DNN on a representative image data set.

Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components

no code implementations7 Feb 2022 Radu Calinescu, Calum Imrie, Ravi Mangal, Genaína Nunes Rodrigues, Corina Păsăreanu, Misael Alpizar Santana, Gricel Vázquez

We use the method in simulation to synthesise controllers for mobile-robot collision mitigation and for maintaining driver attentiveness in shared-control autonomous driving.

Autonomous Driving Decision Making

DeepCert: Verification of Contextually Relevant Robustness for Neural Network Image Classifiers

no code implementations2 Mar 2021 Colin Paterson, Haoze Wu, John Grese, Radu Calinescu, Corina S. Pasareanu, Clark Barrett

We introduce DeepCert, a tool-supported method for verifying the robustness of deep neural network (DNN) image classifiers to contextually relevant perturbations such as blur, haze, and changes in image contrast.

Maintaining driver attentiveness in shared-control autonomous driving

no code implementations5 Feb 2021 Radu Calinescu, Naif Alasmari, Mario Gleirscher

We present a work-in-progress approach to improving driver attentiveness in cars provided with automated driving systems.

Autonomous Driving Robotics Systems and Control Systems and Control

Fast Parametric Model Checking through Model Fragmentation

no code implementations2 Feb 2021 Xinwei Fang, Radu Calinescu, Simos Gerasimou, Faisal Alhwikem

Parametric model checking (PMC) computes algebraic formulae that express key non-functional properties of a system (reliability, performance, etc.)

Software Engineering Formal Languages and Automata Theory Robotics

Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)

1 code implementation2 Feb 2021 Richard Hawkins, Colin Paterson, Chiara Picardi, Yan Jia, Radu Calinescu, Ibrahim Habli

Machine Learning (ML) is now used in a range of systems with results that are reported to exceed, under certain conditions, human performance.

BIG-bench Machine Learning

Detection and Mitigation of Rare Subclasses in Deep Neural Network Classifiers

no code implementations28 Nov 2019 Colin Paterson, Radu Calinescu, Chiara Picardi

Regions of high-dimensional input spaces that are underrepresented in training datasets reduce machine-learnt classifier performance, and may lead to corner cases and unwanted bias for classifiers used in decision making systems.

Decision Making

Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges

no code implementations10 May 2019 Rob Ashmore, Radu Calinescu, Colin Paterson

Our paper provides a comprehensive survey of the state-of-the-art in the assurance of ML, i. e. in the generation of evidence that ML is sufficiently safe for its intended use.

BIG-bench Machine Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.