Identifying vegetation from laser data in structured outdoor environments

• Published in: Robotics and autonomous systems 2014-05, Vol.62 (5), p.675-684
• Main Authors: Wurm, Kai M., Kretzschmar, Henrik, Kümmerle, Rainer, Stachniss, Cyrill, Burgard, Wolfram
• Format: Article
• Language: English
• Subjects: Autonomous; Autonomous navigation; Classification; Classifiers; Laser reflectivity; Lasers; Outdoor; Robots; Self-supervised learning; Terrain classification; Vegetation; Vegetation detection
• ISSN: 0921-8890; 1872-793X
• DOI: 10.1016/j.robot.2012.10.003

The ability to reliably detect vegetation is an important requirement for outdoor navigation with mobile robots as it enables the robot to navigate more efficiently and safely. In this paper, we present an approach to detect flat vegetation, such as grass, which cannot be identified using range measurements. This type of vegetation is typically found in structured outdoor environments such as parks or campus sites. Our approach classifies the terrain in the vicinity of the robot based on laser scans and makes use of the fact that plants exhibit specific reflection properties. It uses a support vector machine to learn a classifier for distinguishing vegetation from streets based on laser reflectivity, measured distance, and the incidence angle. In addition, it employs a vibration-based classifier to acquire training data in a self-supervised way and thus reduces manual work. Our approach has been evaluated extensively in real world experiments using several mobile robots. We furthermore evaluated it with different types of sensors and in the context of mapping, autonomous navigation, and exploration experiments. In addition, we compared it to an approach based on linear discriminant analysis. In our real world experiments, our approach yields a classification accuracy close to 100%. ► Approach for detecting flat vegetation, such as grass, using laser range scanners. ► SVM-based classification system that yields an accuracy of close to 100%. ► Self-supervised acquisition of training data to avoid manual labeling. ► Alternative classification approach for resource-constraint systems. ► Extensive evaluation in real world experiments using different robots and sensors.