AI to Manipulate Objects, Seen For a 1st Time

New system that helps robots to manipulate objects is called Dense Object Nets and is developed by the Massachusetts Institute of Technology scientist
12 September 2018   844

Researchers from the Massachusetts Institute of Technology (MIT) have developed a system for robots called Dense Object Nets (DON), which interacts with objects of an unfamiliar form. It virtually decomposes the object into its constituent parts, remembers its characteristics and the way it interacts with it. When the algorithm encounters a new object, it tries to understand whether its parts are similar to those seen previously.

The system examines the object at different angles using cameras on the manipulator, then recognizes the images and determines the coordinates of all points of the object. On average, the analysis takes about 20 minutes.

During the training, the researchers showed the DON sneakers and taught the system to raise it in a certain way. When the algorithm first saw another shoe in different angles, it realized that it had a similar object in front of it, and raised it in the same way.

Another example is a mug with a liquid. Unlike most similar systems, DON can lift it by the handle, even if it stands upright or upside down.

Founders of DON hope that their technology will find use in warehouses of such large retailers as Amazon and Walmart. In addition, robots can work as house helper.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   671

NVIDIA has released the source code for the SPADE machine learning system (GauGAN), which allows for the synthesis of realistic landscapes based on rough sketches, as well as training models associated with the project. The system was demonstrated in March at the GTC 2019 conference, but the code was published only yesterday. The developments are open under the non-free license CC BY-NC-SA 4.0 (Creative Commons Attribution-NonCommercial-ShareAlike 4.0), allowing use only for non-commercial purposes. The code is written in Python using the PyTorch framework.

Sketches are drawn up in the form of a segmented map that determines the placement of exemplary objects on the scene. The nature of the generated objects is set using color labels. For example, a blue fill turns into sky, blue into water, dark green into trees, light green into grass, light brown into stones, dark brown into mountains, gray into snow, a brown line into a road, and a blue line into the river. Additionally, based on the choice of reference images, the overall style of the composition and the time of day are determined. The proposed tool for creating virtual worlds can be useful to a wide range of specialists, from architects and urban planners to game developers and landscape designers.

Objects are synthesized by a generative-adversarial neural network (GAN), which, based on a schematic segmented map, creates realistic images by borrowing parts from a model previously trained on several million photographs. In contrast to the previously developed systems of image synthesis, the proposed method is based on the use of adaptive spatial transformation followed by transformation based on machine learning. Processing a segmented map instead of semantic markup allows you to achieve an exact match of the result and control the style.

To achieve realism, two competing neural networks are used: the generator and the discriminator (Discriminator). The generator generates images based on mixing elements of real photos, and the discriminator identifies possible deviations from real images. As a result, a feedback is formed, on the basis of which the generator begins to assemble more and more qualitative samples, until the discriminator ceases to distinguish them from the real ones.