Actively Enhanced Cognition-based Framework for Design of Complex Systems (AGNOSTIC)

A novel technical framework to simplify the design and operation of complex systems in areas such as automotive radar, caching, and wireless networks.

The project at a glance

Start date:

01 Oct 2017
Duration in months:

60
Funding:

EUROPEAN COMMISSION – ERC
Principal Investigator(s):

Björn Ottersten

About

Many automated systems, such as parking assist systems in cars, process data acquired from sensors and make decisions autonomously based on machine learning, a sub-field of artificial intelligence. However, such systems can be enhanced using mathematical models. For example, in parking assist systems, a mathematical model provides methods for focusing the scan area around the vehicle to obtain reliable data about the scene. The intelligent algorithms can then better recognise from the sensor data that there are, for example, a bin and a person nearby. The model focuses automatically on the person as the critical element. Currently, such models are developed on a case-by-case basis – a time-consuming process. But AGNOSTIC provides a framework to streamline their development. In particular, the aim of the AGNOSTIC project is to combine two established models for signal processing using artificial intelligence techniques in order to enhance the way such complex systems function. The research path includes exploring new radar technologies, which leads to the development of a novel, high performance radar system that would enable efficient target detection and tracking.