PICK-PLACE focuses on flexible, safe and dependable robotic part-handling in industrial environments. The project proposes a combination of human and robot capabilities in order to achieve this efficient hybrid pick-and-place / pick-and-package solution. It includes dynamic package configuration, flexible grasping strategies using an innovative multifunctional gripper, robust environment perception and mechanisms and strategies for human-robot collaboration.
Due to the large number of references that the system needs to be able to cope with, we are using a deep learning based approach for object identification, segmentation and grasping point selection.
There are different steps involved in order to generate a deep learning model. First, a dataset with images of different objects needs to be generated. Scenes with different number of objects in different positions and poses are generated. Then, all the pictures need to be labeled.
These questions are fundamental in a human-robot collaboration scenario. Task 1.2 of the PICK-PLACE project analyzes the role of motion-planner behavior on the operator’s feelings.
An experimental campaign has been used to understand how humans are affected in their jobs by the presence of a robot. The results have been described in Deliverable 1.2. This post offers a brief summary of the most relevant conclusions. Read more
Source: The International Journal of Robotics Research
Authors: Mohamad Javad Aein, Eren Erdal Aksoy, Florentin Wörgötter
Publication: First published
Source: Spectrum IEEE / by Erico Guizzo
The company, famous for agile machines like Atlas and Spot, wants to unleash