H2020 METRICS project is organizing a Sim2Real object perception challenge in the field of agile production.

In the challenge, the task is to detect and recognize different parts of a gear assembly system and to estimate their position and orientation. The goal here is to assess the performance of detection, classification and pose-estimation algorithms that have limited access to real data during the training phase. Participants can use the provided CAD models of these parts to develop and train their algorithms. The actual test phase however, will be done using real images of the actual objects.

The challenge is part of the ADvanced Agile ProducTion (ADAPT) competition and will be hosted on codalab.

Participation is open to the public, as individuals or teams: https://metricsproject.eu/agile-production/2nd-cascade-campaign-2023/

The challenge consists of two consecutive phases:
Validation Phase:              27/09/2023 – 05/11/2023
Test Phase:                          06/11/2023 – 17/11/2023

To participate:
Object detection: https://codalab.lisn.upsaclay.fr/competitions/15873

Pose estimation: https://codalab.lisn.upsaclay.fr/competitions/15874

For more information, please contact agile.production(a)metricsproject.eu

ADAPT (Advanced Agile ProDuction) is part of the METRICS project funded by the European Union’s Horizon 2020 research and innovation program.
METRICS is dedicated to evaluation campaigns (both field and cascade challenges) to assess the technological maturity of robotic and Artificial Intelligence (AI) systems for four different sectors. The project is coordinated by the French national laboratory for metrology and testing (LNE) in partnership with sixteen European organizations.

Dr. Roel Pieters, Associate Professor

Cognitive Robotics

Faculty of Engineering and Natural Sciences,

Automation Technology and Mechanical Engineering

Tampere University, Finland

+358 50 447 8347

email: roel.pieters(at)tuni.fi

https://research.tuni.fi/cogrob