Hierarchical memory structure for the real-time search for action acquisition of an autonomous mobile robot

This paper proposes a new memory structure for the real-time search with the computational resource boundary. In the proposed memory, each memory is hierarchically stored based an the frequency recall. Moreover, the number of checked memories is varied based on the available computational resource for the action acquisition in order to treat the trade-off between the computational amount for the memory retrieval and the one of the search. When the search system utilises stored memories, the one with the highest frequency of recall is started checking from. This makes the efficient retrieval possible even if the available computational resource for the memory retrieval is not enough. In this paper, the proposed method is applied to the action acquisition for autonomous mobile robots in the moving obstacles' avoidance problem. Its usefulness is shown through some experimental result's and the verification.