Method and apparatus for agent exploration based on similarity score of topological graph

An agent exploration apparatus comprising:

• a memory for storing instructions;
• and
• a processor for performing a predetermined operation on the basis of the instructions, wherein
• operations of the processor include:
• an operation of generating image information and location information of an exploration region in each search round;
• an operation of generating a first graph structure by setting image information of each search round as a first node, setting location information of each search round as a first edge, and connecting the first node of a current round to the first node of a previous round using the first edge;
• an operation of acquiring second node information of a second graph structure of each search round generated by another agent exploration device;
• an operation of calculating a similarity score between first node information and the second node information in each search round;
• an operation of mapping the similarity score of each search round to the first node of each search round of the first graph structure;
• and
• an operation of determining a search region of a next round on the basis of the similarity score mapped to the first node of the first graph structure.

A computer program stored in a computer-readable recording medium and including instructions executed on at least one processor to perform, by the processor,

• an operation of generating image information and location information of an exploration region in each search round;
• an operation of generating a first graph structure by setting image information of each search round as a first node, setting location information of each search round as a first edge, and connecting the first node of a current round to the first node of a previous round using the first edge;
• an operation of acquiring second node information of a second graph structure of each search round generated by another agent exploration device;
• an operation of calculating a similarity score between first node information and the second node information in each search round;
• an operation of mapping the similarity score of each search round to the first node of each search round of the first graph structure;
• and
• an operation of determining a search region of a next round on the basis of the similarity score mapped to the first node of the first graph structure.