Probabilistic terrain classification in unstructured environments

Authors:
Marcel Häselich;Marc Arends;Nicolai Wojke;Frank Neuhaus;Dietrich Paulus
Affiliations:
Active Vision Group, AGAS Robotics, Department of Computer Sciences, University of Koblenz-Landau, Universitätsstr.1, Koblenz, Germany;Active Vision Group, AGAS Robotics, Department of Computer Sciences, University of Koblenz-Landau, Universitätsstr.1, Koblenz, Germany;Working Group Realtime Systems, Department of Computer Sciences, University of Koblenz-Landau, Universitätsstr.1, Koblenz, Germany;Active Vision Group, AGAS Robotics, Department of Computer Sciences, University of Koblenz-Landau, Universitätsstr.1, Koblenz, Germany;Active Vision Group, AGAS Robotics, Department of Computer Sciences, University of Koblenz-Landau, Universitätsstr.1, Koblenz, Germany
Venue:
Robotics and Autonomous Systems
Year:
2013

Citing 13
Cited 0

Estimating 3-D rigid body transformations: a comparison of four major algorithms

Machine Vision and Applications - Special issue on performance evaluation
Image segmentation using Markov random field model in fully parallel cellular network architectures

Real-Time Imaging
Robot Pose Estimation in Unknown Environments by Matching 2D Range Scans

Journal of Intelligent and Robotic Systems
Color Image Segmentation Based on Markov Random Field Clustering for Histological Image Analysis

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Obstacle Detection and Terrain Classification for Autonomous Off-Road Navigation

Autonomous Robots
Autonomous Navigation of an Unmanned Ground Vehicle in Unstructured Forest Terrain

LAB-RS '08 Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems
Pattern Recognition, Fourth Edition

Pattern Recognition, Fourth Edition
Model based vehicle detection and tracking for autonomous urban driving

Autonomous Robots
Improving robot navigation in structured outdoor environments by identifying vegetation from laser data

IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
Terrain drivability analysis in 3D laser range data for autonomous robot navigation in unstructured environments

ETFA'09 Proceedings of the 14th IEEE international conference on Emerging technologies & factory automation
Unsupervised image segmentation using a simple MRF model with a new implementation scheme

Pattern Recognition
Parametric models of linear prediction error distribution for color texture and satellite image segmentation

Computer Vision and Image Understanding
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Autonomous navigation in unstructured environments is a complex task and an active area of research in mobile robotics. Unlike urban areas with lanes, road signs, and maps, the environment around our robot is unknown and unstructured. Such an environment requires careful examination as it is random, continuous, and the number of perceptions and possible actions are infinite. We describe a terrain classification approach for our autonomous robot based on Markov Random Fields (MRFs ) on fused 3D laser and camera image data. Our primary data structure is a 2D grid whose cells carry information extracted from sensor readings. All cells within the grid are classified and their surface is analyzed in regard to negotiability for wheeled robots. Knowledge of our robot's egomotion allows fusion of previous classification results with current sensor data in order to fill data gaps and regions outside the visibility of the sensors. We estimate egomotion by integrating information of an IMU, GPS measurements, and wheel odometry in an extended Kalman filter. In our experiments we achieve a recall ratio of about 90% for detecting streets and obstacles. We show that our approach is fast enough to be used on autonomous mobile robots in real time.