Autonomous road detection and modeling for UGVs using vision-laser data fusion

Abstract Autonomous road detection and modeling play a key role for UGVs navigating in complex outdoor environments. This paper investigates road detection and description for UGVs in various outdoor scenes under different weather conditions. A novel environment perception system that includes two cameras and multiple laser range finders is introduced firstly. Taking classification accuracy and time-cost into account, 8-dimensional features are selected from a 91-dimensional candidate feature set using Adaboost algorithm. To adapt to the diversity of road scenes under different weather conditions in different seasons, an online classifier based on SVM is proposed to replace the fixed one. Moreover, a road region adjusting algorithm is present to eliminate misclassified regions especially when the roads have fuzzy boundaries or obstacles. Finally, a RANSAC spline fitting algorithm is adopted to provide an accurate road border model for UGVs’ autonomous path planning and navigation. A series of experiments are conducted by using a self-built UGV platform and experimental results show the validity and practicality of the proposed approaches.

[1]  Huosheng Hu,et al.  Real-time road detection and description for robot navigation in an unstructured campus environment , 2014, Proceeding of the 11th World Congress on Intelligent Control and Automation.

[2]  Paul Newman,et al.  Online generation of scene descriptions in urban environments , 2008, Robotics Auton. Syst..

[3]  Lei Zou,et al.  On Global Smooth Path Planning for Mobile Robots using a Novel Multimodal Delayed PSO Algorithm , 2017, Cognitive Computation.

[4]  Rainer Lienhart,et al.  Empirical Analysis of Detection Cascades of Boosted Classifiers for Rapid Object Detection , 2003, DAGM-Symposium.

[5]  Huosheng Hu,et al.  Visual Campus Road Detection for an UGV Using Fast Scene Segmentation and Rapid Vanishing Point Estimation , 2014 .

[6]  Zehong Yang,et al.  A Real-Time Drivable Road Detection Algorithm in Urban Traffic Environment , 2012, ICCVG.

[7]  Mohamed Aly,et al.  Real time detection of lane markers in urban streets , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[8]  Donald Scott,et al.  Shape-guided superpixel grouping for trail detection and tracking , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[10]  David Salomon,et al.  Curves and surfaces for computer graphics , 2005 .

[11]  Huosheng Hu,et al.  Automatic Extrinsic Self-Calibration for Fusing Data From Monocular Vision and 3-D Laser Scanner , 2014, IEEE Transactions on Instrumentation and Measurement.

[12]  Junqiang Xi,et al.  Self‐supervised learning to visually detect terrain surfaces for autonomous robots operating in forested terrain , 2012, J. Field Robotics.

[13]  Zidong Wang,et al.  A new genetic algorithm approach to smooth path planning for mobile robots , 2016 .

[14]  Nelson Alves,et al.  Swarm-based visual saliency for trail detection , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Zhenhua Guo,et al.  Rotation invariant texture classification using LBP variance (LBPV) with global matching , 2010, Pattern Recognit..

[16]  Jean Ponce,et al.  General Road Detection From a Single Image , 2010, IEEE Transactions on Image Processing.

[17]  Matti Pietikäinen,et al.  Dynamic texture and scene classification by transferring deep image features , 2015, Neurocomputing.

[18]  Li Bai,et al.  Robust Road Modeling and Tracking Using Condensation , 2008, IEEE Transactions on Intelligent Transportation Systems.