Evalds Urtans

This paper introduces a novel variant of the Triplet Loss function that converges faster and gives better results. This function can separate class instances homogeneously through the whole embedding space. With Exponential Triplet Loss function we also introduce a novel type of embedding space regularization Unit-Range and Unit-Bounce that utilizes euclidean space more efficiently and resembles features of the cosine distance. We also examined factors for choosing the best embedding vector… Show more

This paper introduces a novel variant of the Triplet Loss function that converges faster and gives better results. This function can separate class instances homogeneously through the whole embedding space. With Exponential Triplet Loss function we also introduce a novel type of embedding space regularization Unit-Range and Unit-Bounce that utilizes euclidean space more efficiently and resembles features of the cosine distance. We also examined factors for choosing the best embedding vector size for specific embedding spaces. Finally, we also demonstrate how new function can train models for one-shot learning and re-identification tasks. Show less

Value Iteration Algorithm is iterative and can’t be parallelized. Computation time grows exponentially when the size of the input maps is increased. We propose UNet-RNN- Skip artificial neural network architecture that can be used to parallelize Value Iteration Algorithm results. The proposed model can solve Value Iteration problem in fewer iterations than the original algorithm and computation time increases by only a small amount when increasing the size of the input map. Fundamental… Show more

Value Iteration Algorithm is iterative and can’t be parallelized. Computation time grows exponentially when the size of the input maps is increased. We propose UNet-RNN- Skip artificial neural network architecture that can be used to parallelize Value Iteration Algorithm results. The proposed model can solve Value Iteration problem in fewer iterations than the original algorithm and computation time increases by only a small amount when increasing the size of the input map. Fundamental UNet-RNN-Skip architecture can be used also to solve and parallelize other sequential problems. With this paper synthetic dataset of maps and generator has been published to enable further studies in mapping and path planning tasks. Show less

Q-value function models based on variations of Deep Q-Network (DQN) have shown good results in many virtual environments. In this paper, over 30 sub-algorithms were surveyed that influence the performance of DQN variants. Important stability and repeatability aspects of state of art Deep Reinforcement Learning algorithms were found. Multi Deep Q-Network (MDQN) as a generalization of popular Double Deep Q-Network (DDQN) algorithm was developed. Visual representations of a learning process as… Show more

Q-value function models based on variations of Deep Q-Network (DQN) have shown good results in many virtual environments. In this paper, over 30 sub-algorithms were surveyed that influence the performance of DQN variants. Important stability and repeatability aspects of state of art Deep Reinforcement Learning algorithms were found. Multi Deep Q-Network (MDQN) as a generalization of popular Double Deep Q-Network (DDQN) algorithm was developed. Visual representations of a learning process as Q-Value maps were produced using PyGame Learning Environment. Videos of trained models available in following link Show less

Our research is proposing an algorithm and technical implementation of a system that can recognize positions and orientations of IR (Infrared) LED (Light Emitting Diode) markers that are invisible to a naked human eye. System is made to work with Oculus Rift DK2 head-mounted display coupled with a 111Hz IR Leap Motion camera. It adds functionality to these devices by allowing them to track different kinds of objects using active IR markers. Up to now most common way for tracking markers for… Show more

Our research is proposing an algorithm and technical implementation of a system that can recognize positions and orientations of IR (Infrared) LED (Light Emitting Diode) markers that are invisible to a naked human eye. System is made to work with Oculus Rift DK2 head-mounted display coupled with a 111Hz IR Leap Motion camera. It adds functionality to these devices by allowing them to track different kinds of objects using active IR markers. Up to now most common way for tracking markers for augmented reality were using fiducial markers that are visible to human eye or other static markers. Such marker systems require flat surface for attaching sticker of a fiducial marker. With our system it is possible to create invisible markers and they can be attached to objects without flat surfaces. As a proof of concept we made a virtual ping-pong game where player uses a physical table tennis paddle fitted with active IR markers. At the time of research, no such tracking systems were available in public domain. Currently similar commercial systems are in development by Oculus and other companies. Limitations of hardware that we found in our research might be one of the main reasons why commercial product is not yet completed. In case of Oculus Rift's IR camera, it has insufficient 30Hz frame-rate to support active IR markers. We found that even with capture rate of 111Hz proposed system works 3 times slower than conventional fiducial markers, but starting at this frame-rate it can be applied for real-time applications. Show less

Research of HLA class 2 genotypes of HIV patients. Machine learning algorithms were used for data mining.

The paper presents practical and theoretical results acquired during a scientific project addressing multi-robot control and management challenges with possible application in greenhouse automation solutions. The main focus of the paper is path planning of mobile robots addressing computation time and memory constraints in embedded robotic systems. The paper presents an analysis that is based on practically experienced cases and proposes modifications of the discussed RRT-based methods in order… Show more

The paper presents practical and theoretical results acquired during a scientific project addressing multi-robot control and management challenges with possible application in greenhouse automation solutions. The main focus of the paper is path planning of mobile robots addressing computation time and memory constraints in embedded robotic systems. The paper presents an analysis that is based on practically experienced cases and proposes modifications of the discussed RRT-based methods in order to ensure better quality of the planning result as well as saved time in specific cases. A key factor of the compareson analysis is time and memory usage that usually are limited in embedded devices like small scale mobile robots. The paper also presents experiment results collected using a prototype robotic system. Show less