Robot navigation and manipulation based on a predictive associative memory

摘要

Proposed in the 1980s, the sparse distributed memory (SDM) is a model of an associative memory based on the properties of a high dimensional binary space. This model has received some attention from researchers of different areas and has been improved over time. However, a few problems have to be solved when using it in practice, due to the non-randomness characteristics of the actual data. We tested an SDM using different forms of encoding the information, and in two different domains: robot navigation and manipulation. Our results show that the performance of the SDM in the two domains is affected by the way the information is actually encoded, and may be improved by some small changes in the model.