Autonomous driving represents the greatest disruption in mobility since the invention of the car. It will not only radically transform the way we travel, but also boost the safety, comfort and efficiency of vehicles to a level beyond imagination.
Autonomous vehicles require maps that are significantly different from the maps that are used in today’s navigation systems. In order to operate safely, efficiently and in a comfortable way for passengers, autonomous vehicles need high-definition maps that allow for centimeter-level accuracy. HD Maps also need to be updated frequently, to reflect changes such as lane closures, roadworks and updated speed limits.
TomTom HD Maps enable path planning, aid perception, and allow an autonomous vehicle to see and anticipate the road ahead even beyond the range of its sensors. Enabled by its real-time map infrastructure, TomTom HD Maps provide a highly accurate and realistic representation of the roadway profile, including key elements such as 3D geometry, lane markings and road furniture. TomTom HD Maps are not limited to autonomous vehicles, but can also be leveraged to fulfil a broad range of ADAS applications such as predictive powertrain control, eco-routing and curve speed warnings.
To further scale up our HD mapmaking and map maintenance, we extract map data such as road geometry, traffic signs and landmarks from camera images. This type of data is particularly relevant when it comes to updating an HD Map to reflect reality, for example when it is used to perform object-based localisation.
The first generation of the TomTom HD Map focuses on highway driving; support for other environments, both urban and rural, will follow as autonomous driving evolves.
A key challenge of autonomous driving is determining the exact location of an autonomous vehicle on the road. In order to operate safely and efficiently, it is key for an autonomous vehicle to be able to locate itself on a specific lane with extreme accuracy. Today’s navigation systems use traditional GPS for localisation; however, traditional GPS fails to deliver the needed level of accuracy and robustness to enable autonomous driving.
To address this challenge, TomTom has developed RoadDNA, a localisation layer in the TomTom HD Map that enables accurate and robust localisation for autonomous vehicles. TomTom’s patented RoadDNA technology delivers a highly optimised, 3D lateral and longitudinal view of the roadway. With this, a vehicle can correlate RoadDNA data with data obtained by its own sensors. By doing this correlation in real time, TomTom RoadDNA precisely locates a vehicle on the road, even while travelling at high speeds.
By converting a 3D point cloud of roadside patterns into a compressed, 2D view of the roadway, TomTom RoadDNA delivers a solution that can be used in-vehicle with limited processing requirements. Without losing roadway detail, TomTom RoadDNA follows a feature-agnostic approach which is robust and scalable. This technique eliminates the complexity of identifying each single roadway object, but rather creates a unique pattern of the roadway environment.
For a safe and comfortable experience, an autonomous vehicle needs to anticipate the road ahead. To do that, it needs a horizon made up of sensor data and map data.
TomTom AutoStream enables vehicles to build a horizon for the road ahead by streaming the latest map data from the TomTom cloud. By ensuring that the map used to power advanced driving functions is always the latest, the TomTom AutoStream enhances driver safety.
In practice, as a driver enters a route in the navigation system, the route is shared with the TomTom cloud. AutoStream streams the latest and most relevant map data back to the car, to be used by ADAS and Autonomous Driving applications. If the car drives without a route, AutoStream can use “hints” such as the current vehicle position or a most probable path to determine what map data to stream to the car.
TomTom AutoStream is designed in a flexible way, allowing customers to customize the map data stream based on criteria such as sensor configuration and horizon length. It can stream Advanced Driving Attributes such as gradient and curvature, HD Map, and Live data such as dynamic speed limits and traffic information. This flexibility allows customers to use AutoStream to power lower automation functions, as well as higher automation functions.
TomTom AutoStream comes as a full solution including on-board software which significantly simplifies and shortens development time for companies building autonomous driving systems. TomTom AutoStream ensures that the map data used to power advanced driving functions is always the latest available, enabling a safe and comfortable experience.