Best Research Paper Candidate PDF Print E-mail
Announcements

 

Paper "On failures of RGB cameras and their effects in autonomous driving applications" from
Francesco Secci and Andrea Ceccarelli was shortlisted as Best Research Paper Candidate at ISSRE 2020 (31st International Symposium on Software Reliability Engineering)! Check the paper and the tool (also on github)! 

You can see the list of Best Research paper Candidates and all papers accepted at ISSRE 2020 at http://2020.issre.net/research-accepted-papers#best_papers
 

 
Emulation of Camera Failure PDF Print E-mail
Tools

A python library that aims to simulate failures that may occur in a camera during the acquisition/processing phase.

To support the definition of safe and robust vehicle architectures and intelligent systems, we define the failures model of a vehicle camera, together with an analysis of effects and known mitigations. As a natural consequence, here we present a software library for the generation of the corresponding failed images. These images are then fed the trained agent of an autonomous driving simulator: the misbehavior of the trained agent allows a better understanding of failures effects and especially of the resulting safety risk. 

Some examples of the failures injected:

GoldenRun

Github is available at: https://github.com/francescosecci/Python_Image_Failures

More information:

  • Thesis of Francesco Secci, "On failures of RGB cameras and their effects in autonomous driving applications", Master Thesis at the University of Florence, Italy (in Italian only), July 2020. Supervisor: Andrea Ceccarelli (link to thesis page)
  • Paper: Francesco Secci, Andrea Ceccarelli, "On failures of RGB cameras and their effects in autonomous driving applications", in press -- to appear at the 31st International Symposium on Software Reliability Engineering (ISSRE 2020), available on arXiv

GoldenRun

NOISE

BLUR

Broken Lens

Brightness

Sharpness

Chromatic Aberration

ICE

DIRT

 
ADVANCE PDF Print E-mail
ADVANCE

Involvment type: coordinator

Project website: https://www.advance-rise.eu/

Project contract: H2020-MSCA-RISE-2018, number 823788

Start date: 01-01-2019

End date: 31-12-2022

 

The scientific objective of the ADVANCE project is to conceive new approaches to support the Verification and Validation (V&V) of Cyber-Physical Systems (CPS). It will explore techniques, methods, and tools applicable to different phases of the system lifecycle, but always with the final objective of improving the effectiveness and efficacy of the V&V process. In particular, ADVANCE will focus on two main aspects of V&V: i) techniques to collect V&V evidences for a CPS (focusing on system modeling, testing, fault forecast, and systematic processes like FMEA), and ii) techniques to manage and analyze data of the system under analysis (focusing on data analysis, requirements management, traceability). The strategic objective of the project is to build an international network of collaborations on the topic of V&V of CPSs. Besides allowing the consortium to reach the project's scientific objectives, the established interactions would allow the training of students and professionals on the latest innovations in the V&V panorama, and have them work together towards a common goal. In fact, besides the technical challenges described above, an important factor hampering advancements in the V&V of CPSs is a worldwide lack of skilled professionals in V&V, software testing, and Information and Communication Technology (ICT) in general. One of the outputs of the project will be a set of training material, both in the form of slides and video courses, on the topic of Verification & Validation of Cyber-Physical Systems. These objectives will be pursued by joining together V&V experts having different specialization and different backgrounds, and establishing a targeted transfer of knowledge and collaboration program, using two real case studies as reference.

The consortium includes:

    • RCL: CINI, Italy
    • UNIVERSIDADE DE COIMBRA, Portugal
    • BUDAPESTI MUSZAKI ES GAZDASAGTUDOMANYI EGYETEM, Hungary
    • UNIVERSIDAD DE LOS ANDES FUNDACION, Colombia
    • RESILTECH SRL, Italy
    • UNIVERSIDADE ESTADUAL DE CAMPINAS, Brazil
    • INSTITUTO NACIONAL DE PESQUISAS ESPACIAIS, Brazil

This project has received funding from the European Union's H2020-MSCA-RISE-2018, proposal ID 823788.

 

 
RFI - Safety-Critical Architectures PDF Print E-mail
RFI - Safety-Critical Architectures

 

The project explores Safe Architectures for SIL4 Railway Systems. This three-year project will see a cooperation between RCL group and the R&D department of RFI - Rete Ferroviaria Italiana -, which is managing the railway network in Italy. Main targets of the project will be:

- Definition of architectures for two future SIL4 systems: PMF, which will work onboard of the train, and SEC, which will be deployed inside stations.

- Devising coding rules for implementing SIL4 software in the railway domain, including coding rules, coding styles and quality metrics.

- V&V Plan, and definition of Safety Cases

- Preliminary Hazard Analyses

- Modeling activities for the early validation of the systems above both in terms of Safety and Security.

- Exploring mechanisms for fault-tolerance in the railway domain in accordance with standards such as ERTMS / SCMT (Italian)

- Safe Visualization of safety-critical information on commercial OTS devices (e.g., tablets)

- Implementation of the "Protocollo Vitale Standard" to allow safe communications among subsystems.

Overall, the aim of the project is to devise architectures and mechanisms for SIL4 systems, along with prototypes of specific subsystems.

 
SISTER: SIgnaling & Sensing TEchnologies in Railway applications PDF Print E-mail
SISTER

alt

Involvment type: participantalt
Project website:http://www.progetto-sister.com/
Project contract: POR FESR Toscana 2014-2020
Start date: 2017-02-01
End date: 2018-12-31

 

Goals and Objectives

In the context of integration of traditional tramway systems with metropolitan hybrid solutions tram-train type (Light Rail Transit, LRT), the SISTER project aims at combining the concepts of rail safety with a higher operative automation level, guaranteed by innovative signaling solutions. The solutions developed within the SISTER project will allow significant improvements in capacity in LRT systems together with the assurance of fast, safe and efficient journeys.

Design of a solution that will improve safety in LRT mode by the development, integration and validation of three innovative actions:
- An innovative signaling system;
- A new remote sensing radar with a high reliability level;
- An innovative communication system based on radio broadband resilient to interferences.

The maturity level of the solution will be evaluated in a partner gate in order to make the necessary corrections to develop a final demonstrator.

Consortium

  • THALES ITALIA S.P.A.
  • IDS INGEGNERIA DEI SISTEMI S.P.A.
  • GENESY SRL
  • UNIVERSITA’ DEGLI STUDI DI FIRENZE
  • UNIVERSITA’ DI PISA
  • RESILTECH SRL
 
TOSCA-FI: Tool Optoelettronico per Strutture in Calce cemento Acciaio - Ferrovie Italiane PDF Print E-mail
TOSCA-FI

Involvment type: participant
Project contract: FAR-FAS 2014
Start date: 2017-01-01
End date: 2018-12-31

Goals and Objectives

Develop an innovative diagnostic methodology for inspection and control of railway infrastructure such as bridges built in concrete, steel, or masonry,  in order to improve the current systems based only on visual examination.

High-resolution photography and thermography will be integrated with innovative remote-sensing technologies as 3D laser scanner, and fluorescence lidar.

The consortium will study data fusion methodologies necessary to correlate and merge two-dimensional and three-dimensional images aiming at strengthen the information content. Data coming from these different sources will flow into an ICT platform (i.e. a OLAP database) for analysis and historical archiving.

Consortium

  • Te.Si.Fer. S.r.l.
  • DiMaI - Università degli Studi di Firenze
  • IFAC - CNR
  • Durazzani S.r.l. - Territorio e Ambiente
  • IAC - CNR
 
<< Start < Prev 1 2 3 4 5 6 7 8 9 10 Next > End >>

Page 1 of 16

Resilient Computing Lab, 2011

Joomla - Realizzazione siti web