The rapid increase in the importance of human-machine interaction and the accelerating pace of life pose various challenges for the creators of digital environments. Continuous improvement of human-machine interaction requires precise modeling of the physical and emotional state of people. By implementing emotional intelligence in machines, robots are expected not only to recognize and track emotions when interacting with humans, but also to respond and behave appropriately. The machine should match its reaction to the mood of the user as precisely as possible. Music generation with a given emotion can be a good start to fulfilling such a requirement. This article presents the process of building a system generating music content of a specified emotion. As the emotion labels, four basic emotions: happy, angry, sad, relaxed, corresponding to the four quarters of Russell’s model, were used. Conditional variational autoencoder using a recurrent neural network for sequence processing was used as a generative model. The obtained results in the form of the generated music examples with a specific emotion are convincing in their structure and sound. The generated examples were evaluated with two methods, in the first using metrics for comparison with the training set and in the second using expert annotation.
Sonars are among the most popular navigation elements used in autonomous vehicles. Beside their well known properties, they have unexplored specifics offering interesting information. In this paper, we present the results of an experiment with the drawbacks of sonars. Our approach combined the regular information obtained from a sonar system with information deriving from measurement aberration. The experiments with an ultrasonic range measurement system of a mobile robot showed that the usually neglected sonar drawbacks could be unusually helpful. This paper emphasizes the effectiveness of identification, which was calculated based on the ratio of the quantities of parallelepipeds to cylinders. The experimental results are presented. Further work aims to implement this idea on a robot on an HCR base. Another possibility is also suitable implementation of map building with a relative degree of confidence.