Project MaX - MazeXplorer
Project Announcement
| The goal of this four-semester (2005-2007) student project is to develop a VR maze and a set of artificial agents whose task it is to competitively explore the maze. The agents will possess varying object and scene recognition abilities, and visual information will be at the basis of their knowledge acquisition. Project subtasks include the design of suitable action-centered knowledge representation structures and the development of exploration strategies which operate on declarative, rule-based, or analogical environmental knowledge and on uncertain knowledge on actions, among others. The exploration scenario will be game-like. |  |
Project MaX
|
The student's project MaX - MazeXplorer was initiated by the research
groups Cognitive
Neuroinformatics and Cognitive Systems. The research
areas of Cognitive Systems cover knowledge representation, reasoning, spatial cognition as well as the development of spatiotemporal cognitive models. The Cognitive Neuroinformatics research group investigates automated learning, processing and representation of uncertain knowledge and
develops biologically inspired hybrid knowledge-based systems with the use
of neuronal and cognitive processes. The project's goal was the development of a cognitive software agent operating in a virtual environment. The agent should be capable of exploring its environment autonomously by generating a suitable knowledge representation. With the integration of a biologically inspired visual system the process of perception should be connected with the decision making. |
|
| |
aktualisiert: 21.10.07 / sb