Structuring Free Space as a Hypergraph for Roving Robot Path Planning and Navigation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Towards a computational theory of cognitive maps
Artificial Intelligence
Four important issues in cognitive mapping
Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
Representing and acquiring geographic knowledge (robotics)
Representing and acquiring geographic knowledge (robotics)
The Utility of Global Representations in a Cognitive Map
COSIT 2001 Proceedings of the International Conference on Spatial Information Theory: Foundations of Geographic Information Science
Hi-index | 0.00 |
This paper extends Yeap's [1988] computational theory of cognitive maps, focusing on the problem of computing a raw cognitive map by an autonomous agent. In addition to having a 150° view of the environment as input, the agent also maintains a representation of her immediate surroundings. This representation is referred to as an MFIS, a Memory For one's Immediate Surroundings. Arguments for the use of the MFIS are presented. The main questions that we ask in implementing our ideas are: (i) what frame of reference is appropriate for the MFIS? and (ii) how does the MFIS change as the agent moves through the environment? A program has been implemented successfully and the main algorithms used and the results of running the program are presented.