Cascade campaign dry-run

CEA LIST is coordinating the Sim2Real Challenge under ADAPT Competition. In this 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. Object detection and pose estimation are important capabilities for industrial robotic systems. Therefore, being able to train algorithms using CAD models can play a significant role in bringing agility to industrial systems.

The cascade competition is hosted on CodaLab.

In order to participate, please sign up for the individual challenges here:

OBJECT DETECTION CHALLENGE 

OBJECT POSE ESTIMATION CHALLENGE