Abstract

Road boundary detection is an important part of the perception of the autonomous driving. It is difficult to detect road boundaries of unstructured roads because there are no curbs. There are no clear boundaries on mine roads to distinguish areas within the road boundary line and areas outside the road boundary line. This paper proposes a real-time road boundary detection and tracking method by a 3D-LIDAR sensor. The road boundary points are extracted from the detected elevated point clouds above the ground point cloud according to the spatial distance characteristics and the angular features. Road tracking is to predict and update the boundary point information in real-time, in order to prevent false and missed detection. The experimental verification of mine road data shows the accuracy and robustness of the proposed algorithm.

Highlights

  • Many special scenarios require the practical application of autonomous driving including industrial automation, construction, and mining [1]

  • We propose a road boundary point tracking method based on Kalman filter, which can improve the stability and accuracy of detection results

  • At the end of this section, the detection results of autonomous trucks and the handling of missed detection on road boundary points and false detection problems are shown

Read more

Summary

Introduction

Many special scenarios require the practical application of autonomous driving including industrial automation, construction, and mining [1]. Wang et al [5] proposed a double layer beam model method to effectively detect intersection roads. To solve the above challenging problems in the mine environment, this paper proposes a robust and effective method to detect the boundary line of mine roads. We optimize and stabilize the results of road detection through road boundary point tracking. The main contributions of this paper are as follows: We propose a method that can effectively detect the boundaries of mine roads. We propose a road boundary point tracking method based on Kalman filter, which can improve the stability and accuracy of detection results.

Road Boundary Points Extraction
Road Boundary Points Filtering
Road Boundary Detection
Data Preprocessing
Ground Surface Detection
Candidate Points Extraction
Boundary Points Fitting
Road Boundary Tracking
Road Boundary Point Prediction
Road Boundary Points Association
Road Boundary Points Update
Experiment Results
Experimental Setup
Evaluation of the Road Detection Algorithm
Detection Results for Autonomous Truck
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call