A Cognitive Map for an Artificial Agent
نویسندگان
چکیده
We show how a general-purpose cognitive architecture augmented with a general diagrammatic component can represent and reason about Large-scale Space. The diagrammatic component allows an agent built in this architecture to represent information both symbolically and diagrammatically as appropriate. Using examples we show (a) how the agent’s bimodal representation captures its knowledge about large-scale space as well as how it learns this information while problem solving and (b) the agent’s flexibility when it comes to using learned information and incorporating new information in solving problems involving large-scale space.
منابع مشابه
Evaluating cognitive maps for mobile robot navigation behaviour
This paper examines biologically inspired cognitive map models, which provide an artificial navigating agent with a topological map of places after an exploration and learning phase in a previously unknown environment. The evaluation requires analytical methods that either rate the cognitive map on the basis of the map’s features, or that rate the observed behaviour of the navigating agent. Som...
متن کاملDeveloping A Fault Diagnosis Approach Based On Artificial Neural Network And Self Organization Map For Occurred ADSL Faults
Telecommunication companies have received a great deal of research attention, which have many advantages such as low cost, higher qualification, simple installation and maintenance, and high reliability. However, the using of technical maintenance approaches in Telecommunication companies could improve system reliability and users' satisfaction from Asymmetric digital subscriber line (ADSL) ser...
متن کاملA case-based reasoning based multi-agent cognitive map inference mechanism: An application to sales opportunity assessment
In order to propose a new cognitive map (CM) inference mechanism that does not require artificial assumptions, we developed a case-based reasoning (CBR) based mechanism called the CBRMCM (Case-Based Reasoning based Multi-agent Cognitive Map). The key idea of the CBRMCM mechanism involves converting all of the factors (nodes) that constitute the CM into intelligent agents that determine their ow...
متن کاملZ-Cognitive Map: An Integrated Cognitive Maps and Z-Numbers Approach under Cognitive Information
Usually, in real-world engineering problems, there are different types of uncertainties about the studied variables, which can be due to the specific variables under investigation or interaction between them. Fuzzy cognitive maps, which addresses the cause-effect relation between variables, is one of the most common models for better understanding of the problems, especially when the quantitati...
متن کاملReliable Mapping with an Unreliable Positioning System
We describe mapping of an unknown environment by an artificial agent using a Cognitive Map implemented by a neural network. The environment is depicted in terms of the connectivity between spatial places located on a Cartesian grid. It is shown that the agent can provide a reasonably accurate map even in the absence of a completely reliable positioning system. Spatial Learning with a Cognitive ...
متن کامل