Empirical learning in mobile robot navigation

The purpose of this study is to improve the locomotion performance for auto nomous mobile robots in outdoor environments. In this paper improvement of an environment model is called empirical locomotion performance learning. A system avoids wasting time of observations and actions by analyzing data f rom the last run. We propose a method of empirical learning. The method is expressed by rewriting the rules on the trajectory data. Brief route inform ation for navigating a robot is represented with motion directions at inter sections and metric distances between intersections. The behavior of our ro bot is based on a locomotion strategy 'sign pattern-based stereotyped motio n'. The behaviors are implemented on our mobile robot HARUNOBU-4 and tested at our university campus. Experimental results show a robustness of our pr oposed behaviors under dynamic environments with existing obstacles. Furthe rmore, they showed that our proposed rewriting rules improved the locomotio n performance. In particular, searching time was shortened by 87% (from 453 to 61 s) and the travel distance was shortened by 10% (from 173.8 to 157.5 m).