Terrain classification in field environment based on Random Forest for the mobile robot

Abstract

The inherent topographical diversity of field environment makes it difficult to evaluate the traversability of the terrain for mobile robot navigation. In order to guarantee the real-time performance and adaptability of the terrain classification process, we propose a novel terrain classification method based on Random Forest. This method firstly extracts massive candidate features including color, texture and geometric ones, from which a small subset of features with highly relevancy to the specific type of terrain can be then effectively picked out using our well-designed Random Forest-based online feature selection algorithm. This algorithm is introduced to serve as the cornerstone of our classification method exploiting the trait that the importance of the feature variables and generalization error can be calculated during the training process of the random forest classifier. Following that the selected feature subset is used to train a random forest classifier for evaluating the traversability of the terrain. The experimental results show that our feature selection method based on Random Forest can effectively extract the feature subset highly relevant to terrain leading to the proposed classification algorithm achieving high accuracy and ideal classification speed.