A topologically oriented neural network is very efficient in real-time path planning of a mobile robot in dynamic environments. Using a dynamic recurrent neural network to solve the partial differential equation of a potential field in a discrete manner, the problem of obstacle avoidance and path planning of a moving robot can be efficiently solved. A dimensional network used to represent the topology of the robot's workspace, where each network node represents a state associated with a local workspace point. In this paper, two approaches associated with different boundary conditions are proposed, namely, Dirichlet and Neumann conditions. The first approach relies on a field of attraction distributed around the moving target, acting as a unique local extreme in the local network space. The steepest gradients of the network state variables will aim towards the source of the potential field. The second approach considers two attractive and repulsive potential sources associated with the start and destination points. A dynamic neural mesh is used to model the robot workspace. A simulation package has been built and extensive computer experiments were conducted to demonstrate and validate the reliability of the presented approach.
The paper presents the result of the national ITS project “Monitoring
and control of dangerous goods transport with help of GNSS (Global Navigation Satellite System)” within which the practical pilot trial on different traffic infrastructure is tested. The presented solution relates to routě selection of the dangerous goods transport, so monitoring and control of real movement on selected route is automatically reported.
Spatial navigation comprises a widely-studied complex of animal behaviors. Its study offers many methodological advantages over other approaches, enabling assessment of a variety of experimental questions and the possibility to compare the results across different species. Spatial navigation in laboratory animals is often considered a model of higher human cognitive functions including declarative memory. Almost fifteen years ago, a novel dry-arena task for rodents was designed in our laboratory, originally named the place avoidance task, and later a modification of this approach was established and called active place avoidance task. It employs a continuously rotating arena, upon which animals are trained to avoid a stable sector defined according to room-frame coordina tes. This review describes the development of the place avoidance tasks, evaluates the cognitive processes associated with performance and explores the application of place avoidance in the testing of spatial learning after neuropharmacological, lesion and other experimental manipulations., A. Stuchlík ... [et al.]., and Obsahuje bibliografii a bibliografické odkazy
Path planning problem in mobile robotics can be solved in several ways. Often used are probabilistic roadmaps and potential field algorithm. However, adding nonholonomic constraints into part planning algorithm can be difficult for those methods. Therefore the rapidly exploring random trees (RRT) algorithm was examined and paper illustrates its usability in path planning task for both legged (walking) and wheeled mobile robots. The method proved to be capable of coping with limiting constraints and at the same time it is very fast, enabling its use in real time path recalculation when used with localization algorithm. and Obsahuje seznam literatury
Spatial navigation and memory is considered to be a part of the declarative memory system and it is widely used as an animal model of human declarative me mory. However, spatial tests typically involve only static settings, despite the dynamic nature of the real world. Animals, as well as people constantly need to interact with moving objects, other subjects or even with entire moving environments (flowing water, running stairway). Therefore, we design novel spatial tests in dynamic environments to study brain mechanisms of spatial processing in more natural settings with an interdisciplinary approach including neuropharmacology. We also translate data from neuropharmacological studies and animal models into development of novel therapeutic approaches to neuropsychiatric disorders and more sensitive screening tests for impairments of memory, thought, and behavior., A. Stuchlik ... [et al.]., and Obsahuje bibliografii a bibliografické odkazy