10 years ago, market analysts were predicting that automation would leave drivers obsolete by 2020. While that forecast didn’t quite come true, automated driving (AD) has come a long way in the past decade, with SAE Level 3 vehicles already certified in Japan and more expected to arrive on the European market before the end of the year.
To drive safely, automated vehicles need to not only be able to understand the environment surrounding them, they also need to determine their precise location within that environment – also known as localization. By localizing itself, the vehicle can determine its precise relationship to its surroundings. Is it in the middle lane or the right lane? How far away is the curb?
For effective localization, onboard sensors must work together with high-definition (HD) maps. The latter allows vehicles to match what their onboard sensors see with what’s on the map, helping them determine their exact location on the road and plan safe maneuvers. Using the TomTom HD Map with the RoadDNA localization suite in combination with the Valeo SCALA® 3D LiDAR and Drive4U® Locate technology, we can harness multiple sensors and multiple layers of map data to improve the robustness of localization.
Proving the value of multi-sensor localization
A global leader in driving assistance sensors, Valeo is the first company to series-produce an automotive-grade 3D LiDAR laser scanner on a mass-production scale and have them installed in cars. Its Valeo SCALA® 3D laser scanner uses light beams to detect static or moving obstacles, giving the vehicle a 360° view of its surroundings.
In a recent proof of concept, TomTom and Valeo were able to successfully demonstrate multi-sensor localization by using Valeo localization software to accurately match the output from the Valeo SCALA® 3D LiDAR with RoadDNA data from the TomTom HD Map.
RoadDNA consists of sensor-agnostic localization layers in the TomTom HD Map, such as traffic signs and 3D pattern information about the roadside, to enable precise localization across sensors such as camera and LiDAR. This increases safety by creating redundancy for map data and localization, as well as system robustness by using a multi-sensor approach.
Most providers are only able to link one sensor (for example, a camera) with one type of data in the map – a mono-sensor localization approach. If this sensor fails, the vehicle is left unable to localize itself properly. Using a multi-sensor approach – such as in our proof-of-concept with Valeo – avoids this potentially dangerous drawback. It ensures that a vehicle can accurately localize itself even if one sensor fails or is unable to accurately determine its surroundings; for example, because of poor visibility caused by heavy snow or thick fog.
Despite using three different vehicles, with different camera and LiDAR positions, the joint TomTom and Valeo solution enabled localization with high accuracy in separate driving tests in Tokyo, Paris and San Francisco.