Task Segmentation in a Mobile Robot by mnSOM and Clustering with Spatio-temporal Contiguity
Neural Information Processing
Hierarchical Architecture with Modular Network SOM and Modular Reinforcement Learning
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Hi-index | 0.00 |
Proposed is a new approach to task segmentation in a mobile robot by a modular network SOM (mnSOM). In a mobile robot the standard mnSOM is not applicable as it is, because it is based on the assumption that class labels are known a priori. In a mobile robot, only a sequence of data without segmentation is available. Hence, we propose to decompose it into many subsequences, supposing that a class label does not change within a subsequence. Accordingly, training of mnSOM is done for each subsequence in contrast to that for each class in the standard mnSOM. The resulting mnSOM demonstrates good segmentation performance of 94.05% for a novel dataset.