Project description
Making it easier for self-driving cars to avoid collisions due to faults in the electronics
Connected and autonomous vehicle technology will forever change the future of transportation. Self-driving cars will make roads a lot safer and space exploration will receive a massive boost. However, today’s self-driving cars are not yet compliant with international certification as regards dependability requirements. For instance, object detection (important for autonomous vehicles) is still not dependable. The EU-funded PERIOD project will propose solutions. Specifically, it will correlate computing architectures and software reliability analyses with the impact of faults in the vehicle behaviour. PERIOD will reduce the probability of misdetection without the time, power and cost overheads that make traditional fault tolerance solutions unsuitable for automotive or aerospace real-time systems.
Objective
Autonomous vehicles are about to change completely the transportation systems, the automotive and military markets, and burst deep space exploration. However, while autonomous cars are expected to reduce of two-three orders of magnitude the number of traffic accidents and burst space exploration, the current self-driving systems are not yet compliant with ISO26262 dependability requirements to be adopted in large-scale and are not yet sufficiently reliable to be part of a space mission. In particular object detection, a critical task in autonomous vehicles, has been demonstrated to be highly undependable and to be responsible for the great majority of accidents in current self-driving cars prototypes. “Pursuing Efficient Reliability of Object Detection for automotive and aerospace applications” (PERIOD) challenge is to improve the dependability of object detection frameworks in an effective and efficient way. PERIOD aims at analyzing and proposing solutions to overcome the software and hardware dependability issues of object detection. By correlating computing architectures and software reliability analyses with the impact of faults in the vehicle behavior, PERIOD aims at reducing the probability of misdetection without the time, power, and cost overheads that make traditional fault-tolerance solutions unsuitable for automotive or aerospace real-time systems. The proposed action will enable a highly interdisciplinary collaboration between the experienced researcher, a talented associate professor with a significant track record in computer science and computer engineering, and the supervisor, a world leader in test, embedded systems, and computing architectures for automotive/space applications whose group is embedded systems in one of Europe’s leading research institutions.
Fields of science (EuroSciVoc)
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: https://op.europa.eu/en/web/eu-vocabularies/euroscivoc.
CORDIS classifies projects with EuroSciVoc, a multilingual taxonomy of fields of science, through a semi-automatic process based on NLP techniques. See: https://op.europa.eu/en/web/eu-vocabularies/euroscivoc.
- engineering and technologymechanical engineeringvehicle engineeringautomotive engineeringautonomous vehicles
- natural sciencesphysical sciencesastronomyspace exploration
- natural sciencescomputer and information sciencessoftware
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringcomputer hardware
- natural sciencescomputer and information sciencesartificial intelligencecomputer visionobject detection
You need to log in or register to use this function
Programme(s)
Funding Scheme
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Coordinator
10129 Torino
Italy