LearnBiP - Grasp Learning in Industrial Bin-Picking

The LearnBiP experiment aims to utilize the huge amount of data generated in industrial bin picking for the introduction of grasp learning. Additionally, it evaluates the potential of the SCHUNK dexterous hand, SDH-2, for its application in industrial bin picking.

The first aim will be achieved by using a novel concept of grasp densities. The second aim will be achieved in a two-stage process, in which the SDH-2 hand is thoroughly evaluated in a bin-picking context in a controlled lab environment before it is applied to the industrial system.

Two academic partners co-operate with the industrial company Scape Technologies A/S, which is a well-known international company specializing in generic, industrial bin picking.

We anticipate that the LearnBiP experiment will generate the first example of applying grasp learning in industrial robotics, as well as using dexterous hands in industrial production.



Latest Progress

Aug 28, 2012 :  Public Summary Month 5/2012