Nathan Crombez

M²SV is an exploratory project funded by CNRS’ Special Interest Group on Information, Signal, Image and Vision (GDR ISIS). In this project led by UTBM, CIAD lab, CNRS-AIST JRL and UPJV, MIS lab (France) is are both partners. The aim is to enable the direct visual servoing of both the mobile base and the robot arm with a single spherical camera onboard the mobile base.

Goals

• Optimal placement of the spherical camera
• Eye-in-hand spherical vision-based control of the robot base
• Eye-to-hand spherical vision-based control of the robot arm
• Eye-in-hand / eye-to-hand visual servo combination

Period

2023-2025

Funded by

CNRS GDR ISIS

• Our team obtained the first place at the 2023 UTAC challenge in the professional category « autonomous vehicle in urban area ».

• UTBM students of the Artificial Vision training program have received the best runner-up award for their work entitled « Map-based or Mapless Autonomous Vehicles Navigation ? ».

Demonstration of automatic waste sorting with a mobile robot (Robotnik Summit XL + Kinova arm Gen6):

Our work « Integration of ontology reasoning-based monocular cues in deep learning modeling for single image depth estimation in urban driving scenarios » has been accepted for publication in Knowledge-Based Systems Elsevier Journal.

Our work « Depth Estimation Using Deep Learning Guided By
Ontology Reasoning-Based Monocular Cues » has been accepted for publication in the Proceedings of the IEEE 48th Annual Conference of the Industrial Electronics Society (IECON 2022) in the special session Signal and Image Processing and Computational Intelligence.