RCL welcomes you at the 8th Italian Workshop on Embedded Systems (IWES 2023), in Florence, on the 4th and 5th of September!

The Italian Workshop on Embedded Systems is a well established meeting point for the exchange of research experience in Academy and Industry on all aspects of embedded systems.

Students should consider attending the Students' orientation session, where companies will present themselves and interact with students to scout prospective talents.

More information: https://mclabservices.di.uniroma1.it/iwes/2023/

The chair of RCL Group, Andrea Bondavalli, just finished his Keynote speech at The 41st International Symposium on Reliable Distributed Systems (SRDS 2022)

Keynote Details

Title: Dependability Challenges in Safety-Critical Systems: the adoption of Machine learning

Abstract: Machine Learning components in safety-critical applications can perform some complex tasks that would be unfeasible otherwise. However, they are also a weak point concerning safety assurance. We will illustrate two specific cases where ML must be incorporated in SCS with much care. One is related to the interactions between machine-learning components and other non-ML components and how they evolve with training of the former. We argue that it is theoretically possible that learning by the Neural Network may reduce the effectiveness of error checkers or safety monitors, creating a major complication for safety assurance. An example on automated driving is shown. Among the results, we observed that indeed improving the Controller could make the Safety Monitor less effective; to a limit where a training increment makes the Controller's own behavior safer but results in the vehicle to be less safe. The other one regards ML algorithms that perform binary classification as error, intrusion or failure detectors. They can be used in SCS provided that their performance complies with SCS safety requirements. However, the performance analysis of MLs relies on metrics that were not developed with safety in mind and consequently may not provide meaningful evidence to decide whether to incorporate a ML into a SCS. We analyze the distribution of misclassifications and thus show how to better assess the adequacy of a given ML.

Bachelor Theses

Master Theses

PhD Theses

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:

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

Today is the day in which Maria Hafiza Maqsood, PhD student at the RCL group, ends her 1-month secondment at INPE (Instituto Nacional de Pesquisas Espacial) in the Sao Paulo State!

It was a very inspiring secondment within the ADVANCE project, as it allowed to establish connections between UNIFI and INPE researchers. Thanks Maria and thanks Fatima's group at INPE for hosting!

Starting from the middle of November, the Resilient Computing Lab is hosting three brazilian students as part of the DEVASSES project. All of them are coming from Universidade Federal de Alagoas (UFAL), in Maceió, Alagoas, and are supervised by professor Baldoino Neto.

Anderson Santos is a graduate student working on Anomaly Detection Benchmarks, and he will stay in Firenze for six months. Caio Barbosa and Felipe Falcão are both undergraduate students visiting Firenze for three months: Caio is studying an Anomaly Detector Framework and Felipe is addressing the Classification of Anomaly Detection Algorithms.