Pepper the Robot to Get Emotional System

The system for human interaction is developed by Affectiva and called Emotion AI
30 August 2018   893

SoftBank Robotics, which created the humanoid robot Pepper, integrates into the system for interaction with the person Emotion AI from Affectiva. It will teach robot to distinguish joy, disgust, surprise, fear and other emotions.

The algorithm uses Pepper cameras and microphones to recognize anger, contempt, disgust, fear, joy, sadness and surprise. The robot will distinguish between a smile and a grin, and also understand when a person is distracted or wants to sleep.

SoftBank Robotics introduced Pepper in 2015. It can understand speech, respond to the interlocutor and maintain conversation through the tablet in the case. It was created as a companion for single people and an assistant for business. For example, in 2015 it worked for a week at the Margiotta Food & Wine store in Edinburgh, but the management dismissed him because the robot could not cope with the tasks. Pepper's answers were too general and did not help customers find the right products, and it also joked inappropriately.

In March 2018, researchers found vulnerabilities in robots from SoftBank Robotics. Thanks to these findings, intruders can force androids to extort money, show pornography in public places and swear with clients. Although malware was developed for NAO, the same code can be used for Pepper.

Nvidia to Open SPADE Source Code

SPADE machine learning system creates realistic landscapes based on rough human sketches
15 April 2019   875

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.