Unsupervised learning to recognize environments from behavior sequences in a mobile robot

We describe the development of a mobile robot which does unsupervised learning for recognizing environments from behavior sequences. Most studies on recognizing an environment have tried to build precise geometric maps with high sensitive and global sensors. However such precise and global information may not be obtained in real environments. Furthermore unsupervised-learning is necessary for recognition in unknown environments without help of a teacher. Thus we attempt to build a mobile robot which does unsupervised-learning to recognize environments with low sensitivity and local sensors. The mobile robot is behavior-based and does wall-following in enclosures. Then the sequences of behaviors executed in each enclosure are transformed into input vectors for a self-organizing network. Learning without a teacher is done, and the robot becomes able to identify enclosures. Moreover we developed a method to identify environments independent of a start point using a partial sequence. We have fully implemented the system with a real mobile robot, and made experiments for evaluating the ability. As a result, we found out that the environment recognition was done well and our method was adaptive to noisy environments