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.
The use of bin-picking applications is increasing in the industry. Generally speaking, these applications allow to carry out operations of picking up different products from a box, previously chosen through a vision system.
When picking different products, they can be different in shape, weight and form. To ensure that an object is picked up, a technology capable of dealing with these types of situations is necessary. Read more
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.
Source: Spectrum IEEE / by Erico Guizzo
The company, famous for agile machines like Atlas and Spot, wants to unleash
Source: Science Daily
Wearing a sensor-packed glove while handling a variety of objects, MIT researchers have compiled a massive