Description du projet
L’apprentissage profond plonge en eaux profondes
L’importance des robots augmente rapidement pour de nombreuses tâches et applications. Les robots sont souvent plus rapides ou plus précis que les personnes, ils peuvent assimiler bien plus de données, ou bien ils deviennent des substituts capables de se déplacer à des endroits dangereux pour leurs équivalents humains. Les doter de capacités d’apprentissage profond les a rapprochés davantage des personnes sur le plan architectural et fonctionnel, leur permettant ainsi d’atteindre des niveaux inédits de précision en matière de reconnaissance. Le projet DeeperSense, financé par l’UE, renforcera les capacités des robots de demain en matière de perception de l’environnement en utilisant l’intelligence artificielle et l’apprentissage profond pour combiner des informations visuelles et non visuelles tout comme nous le faisons. La première application portera sur l’environnement inconnu et complexe des robots autonomes sous-marins.
Objectif
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
Champ scientifique
- 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
Mots‑clés
Programme(s)
Régime de financement
RIA - Research and Innovation actionCoordinateur
67663 Kaiserslautern
Allemagne