Skip to main content
European Commission logo print header

Deep-Learning for Multimodal Sensor Fusion

Project description

Deep learning heads for deep waters

The importance of robots to numerous tasks and applications is increasing rapidly. Robots are often faster or more accurate than people, or they can assimilate much more data, or perhaps they are surrogates that can travel to places that are dangerous for their human counterparts. Equipping them with the capacity for deep learning has brought them even closer to humans architecturally and functionally, achieving recognition accuracy at unprecedented levels. The EU-funded DeeperSense project will enhance the environmental sensing capability of tomorrow's robots using AI and deep learning to combine visual and non-visual information the way humans do. The first application focus will be on the complicated and unknown environment of underwater autonomous robots.

Objective

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

Call for proposal

H2020-ICT-2018-20

See other projects for this call

Sub call

H2020-ICT-2020-2

Coordinator

DEUTSCHES FORSCHUNGSZENTRUM FUR KUNSTLICHE INTELLIGENZ GMBH
Net EU contribution
€ 862 500,00
Address
TRIPPSTADTER STRASSE 122
67663 Kaiserslautern
Germany

See on map

Region
Rheinland-Pfalz Rheinhessen-Pfalz Kaiserslautern, Kreisfreie Stadt
Activity type
Research Organisations
Links
Total cost
€ 862 500,00

Participants (7)