Detailed road maps are an important building block for autonomous driving. They accelerate creating a semantic environment model within the vehicle and serve as a backup solution when sensors are occluded or otherwise impaired. Due to the required detail of maps for autonomous driving and virtual test drives, creating such maps is quite labor-intensive. While some detailed maps for fairly large regions already exist, they are often in different formats and thus cannot be exchanged between companies and research institutions. To address this problem, we present the first publicly available converter from the OpenDRIVE format to lanelets—both representations are among the most popular map formats. We demonstrate the capabilities of the converter by using publicly available maps.

The development of automotive technologies requires quite a significant amount of time and money. To accelerate this procedure,

the technology of now is strongly based on computer simulations, where the whole vehicle or its parts can be analyzed in a virtual

environment. The behavior of cars, especially equipped with new sensors or assistants, requires long testing, where the automotive

更多

simulators can play a cardinal role. The precise vehicular tests request accurate environmental models. These new kinds of models

are still standardized; one of the pioneer de facto standards is OpenDRIVE. This standard was initially defined to be able to express

all elements with all potential parameters required in high precision simulations. The actual research focused on creating a compliant

virtual model based on mobile mapping measurements. A Leica Pegasus Two mobile mapping system was applied to capture field

data about the selected pilot area, which is the campus of Budapest University of Technology and Economics (BME). The obtained

Lidar point cloud was georeferenced; the merged point cloud is tailored to the driven trajectory, and then it has been evaluated

manually. The acquired land use map is converted – similarly manually – into basic road geometry elements: straight lane and bended

lane segments. These objects are finally compiled into an XML format, which is compliant with the OpenDRIVE standard. The achieved

virtual model has been tested in Driving Scenario Designer of Mathworks Matlab; however, it is promptly ready for use in other widely

applied automotive simulators.

收起

Nicco Dillmann

Global Technology Manager

ASAM

更多

Standards for ADAS and AD development

May 19th 2020

AD Meetup

Ben Engel

Global Technology Manager

收起

GPUs and AIs can acceierate and automate the creation

and updating of HD maps

• Optimizing the pipeiine to Japan roads with ZENRIN’s

更多

mapping experience, knowiedge and big data

Stiii have many technicai chaiienges. Looking forward to

discussing soiutions and coiiaborating with you!

收起

The OpenDRIVE® format provides a common base for describing track-based road networks using Extensible Markup Language (XML) syntax. The data stored in an OpenDRIVE® file describes – in an analytical way – the geometry of roads as well as features along the roads that influence the logics (e.g. lanes, signs, signals).

更多

The format is organized in nodes which can be extended with user-defined data. By this, a high degree of specialization for individual applications is feasible while maintaining the commonality required for the exchange of data between different applications.

收起