Abstract
The generation of digital maps with lane-level resolution is rapidly becoming a necessity, as semi- or fully-autonomous driving vehicles are now commercially available. In this paper, we present a practical real-time working prototype for road lane detection using LiDAR data, which can be further extended to automatic lane-level map generation. Conventional lane detection methods are limited to simple road conditions and are not suitable for complex urban roads with various road signs on the ground. Given a 3D point cloud scanned by a 3D LiDAR sensor, we categorized the points of the drivable region and distinguished the points of the road signs on the ground. Then, we developed an expectation-maximization method to detect parallel lines and update the 3D line parameters in real time, as the probe vehicle equipped with the LiDAR sensor moved forward. The detected and recorded line parameters were integrated to build a lane-level digital map with the help of a GPS/INS sensor. The proposed system was tested to generate accurate lane-level maps of two complex urban routes. The experimental results showed that the proposed system was fast and practical in terms of effectively detecting road lines and generating lane-level maps.
Highlights
Autonomous driving vehicles with various levels of automation from semi-autonomous driving technologies such as adaptive cruise control (ACC) and lane-keeping assist systems (LKAS) to fully-autonomous driving vehicles are commercially available on the market
The data to evaluate the proposed road lane detection method were collected using a vehicle equipped with a 32-channel 3D LiDAR (Velodyne HDR-32E)
Gray points indicate the given 3D point cloud scanned by a 3D LiDAR; blue points indicate the drivable region; yellow points indicate the road marks on the ground; and magenta lines are the final results of the road line detection at each spin of the LiDAR sensor
Summary
Autonomous driving vehicles with various levels of automation from semi-autonomous driving technologies such as adaptive cruise control (ACC) and lane-keeping assist systems (LKAS) to fully-autonomous driving vehicles are commercially available on the market. While conventional digital maps for car navigation are made for human drivers and have road-level resolution, map providers are focusing on generating digital maps with a relatively high resolution. The presence of lane-level digital maps reduces the burden of capacity and eventually the cost of each autonomous driving vehicle. Using conventional digital maps with road-level resolution, an individual autonomous driving vehicle carries excessive burden to fully understand its surroundings to make a decision. If a lane-level map were provided to the vehicle, the path planning process would become considerably simpler and safer so that the individual vehicle would be less obligated to be equipped with very expensive sensors and processors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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
