Descrizione del progetto
L’apprendimento profondo si dirige verso le acque profonde
L’importanza dei robot per diverse mansioni e applicazioni sta aumentando a ritmo sostenuto. Spesso, i robot sono più veloci o precisi delle persone, o riescono ad assimilare una quantità superiore di dati o talora possono sostituire l’uomo recandosi in luoghi pericolosi. Fornire loro la capacità dell’apprendimento profondo li ha resi ancora più simili agli esseri umani dal punto di vista architettonico e funzionale, fino a raggiungere una precisione di riconoscimento senza precedenti. Il progetto DeeperSense, finanziato dall’UE, migliorerà la capacità di rilevamento ambientale dei robot del futuro utilizzando l’IA e l’apprendimento profondo per combinare le informazioni visive e non visive come fanno gli esseri umani. La prima applicazione verterà sull’ambiente complesso e sconosciuto dei robot autonomi subacquei.
Obiettivo
The main objective of DeeperSense is to significantly improve the capabilities for environment perception of service robots to improve their performance and reliability, achieve new functionality, and open up new applications for robotics. DeeperSense adopts a novel approach of using Artificial Intelligence and data-driven Machine Learning / DeepLearning to combine the capabilities of non-visual and visual sensors with the objective to improve their joint capability of environment perception beyond the capabilities of the individual sensors. As one of the most challenging application areas for robot operation and environment perception, DeeperSense chooses underwater robotics as a domain to demonstrate and verify this approach. The project implements DeepLearning solutions for three use cases that were selected for their societal relevance and are driven by concrete end-user and market needs. During the project, comprehensive training data are generated. The algorithms are trained on these data and verified both in the lab and in extensive field trials. The trained algorithms are optimized to run on the on-board hardware of underwater vehicles, thus enabling real-time execution in support of the autonomous robot behaviour. Both the algorithms and the data will be made publicly available through online repositories embedded in European research infrastructures. The DeeperSense consortium consists of renowned experts in robotics and marine robotics, artificial
Campo scientifico
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsautonomous robots
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensors
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
Parole chiave
Programma(i)
Meccanismo di finanziamento
RIA - Research and Innovation actionCoordinatore
67663 Kaiserslautern
Germania