As virtual reality expands from the imaginative worlds of science fiction and pervades every corner of everyday life, it becomes ever more important for students, researchers and professionals alike to understand the many varied aspects of this technology. This scientific monograph aims to provide a comprehensive guide to the theoretical and practical elements of virtual reality, from the mathematical and technological foundations of virtual worlds to the human factors and the applications that enrich our lives: medicine, entertainment, education and others. After providing a brief introduction to the topic, the book describes the kinematic and dynamic mathematical models of virtual worlds. It explores the many ways a computer can track and interpret human movement, then advances through the modalities that make up a virtual world: visual, acoustic and haptic. With these individual elements covered, the book explores the interaction between the human and a virtual environment as well as design principles of such a virtual environment. Finally, it concludes with an examination of different applications, with a focus on augmented reality as a special case. The knowledge is primarily imparted in a VR context, but is also relevant for many other fields.
COBISS.SI-ID: 10171220
The study examines human motions during gait and the possibility of recognizing intended motions based on measurement of current motions. Machine learning was used to develop an algorithm that detects a person’s intention to begin or stop walking based on lower limb acceleration and foot-ground contact forces. The developed algorithm is intended for use with active exoskeletons and prostheses that provide impaired people with active assistance in response to detected intentions.
COBISS.SI-ID: 10060884
In this study, we developed an algorithm that uses multiple measurements (electroencephalography, electrooculography, camera-based eye tracking, electromyography, hand tracking and the user’s preferences) to dynamically predict the target of a reaching motion. The algorithm is based on supervised machine learning and intelligently switches between measurement modalities to maximize prediction accuracy. It is meant for general use in human-machine interaction, and is currently being integrated with an exoskeleton that actively supports the intended motions.
COBISS.SI-ID: 37005317
The research is related to sensory systems for human-robot interaction. A sensor technology for the measuring of the physical human-robot interaction using pressure based sensors was developed and tested. The system is composed of flexible matrices of opto-electronic sensors covered by a soft silicone cover. Additionally system is battery powered and data transfer is wireless, enabling it for use in both the stationary human-robot systems as well as with wearable robots. This sensory system is completely modular and scalable, allowing one to cover areas of any sizes and shapes, and to measure different pressure ranges. Sensors were used as a layer between the human limb and a wearable robot segment which supports and augments the user’s limb, as well in shoes as a sensorised insole to measure forces under the user’s feet. Sensors were tested for monitoring human-robot interaction in upper- and lower-limb exoskeletons for rehabilitation.
COBISS.SI-ID: 9603156
This paper describes a custom, material-type-independent laser-triangulation-based measurement system that utilizes a high-quality ultraviolet laser beam. Laser structuring applications demand material surface alignment regarding the laser focus position, where fabrication conditions are optimal. Robust alignment of various material types was solved by introducing dynamic symmetrical pattern projection, and a “double curve fitting” centroid detection algorithm with subsurface scattering compensation. Experimental results have shown that the measurement system proves robust to laser intensity variation, with measurement bias lower than 50 μm and standard deviation lower than 6.3 μm for all materials. The developed probe has been integrated into a PCB prototyping system for material referencing purposes.
COBISS.SI-ID: 9813332