How do HD maps extend the vision of autonomous vehicles?

As the world races towards an autonomous future, vehicles require a new generation of highly accurate and realistic digital maps. The groundbreaking TomTom HD Map supports all levels of autonomous driving to bring our vision of a safer, cleaner and less congested world one step closer to reality.

In the coming years, we will see an increase in the number of cars with some form of assisted or automated driving technology. And for good reason. Autonomous driving is bound to increase personal safety, create new mobility options, improve efficiency and give drivers more free time.

To achieve this, autonomous vehicles will rely on a combination of artificial intelligence, sensors and digital maps. Digital maps allow them to see around curves, through fog and over large vehicles blocking the vision of sensors.

Read on to learn how digital maps work and how TomTom and Elektrobit partnered to make autonomous driving a reality.

Maps for autonomous driving

The next generation of autonomous driving technology requires higher quality and more detailed map content to support sensor data and guarantee driver safety and comfort. TomTom has been developing such digital maps for almost a decade in the form of ADAS Maps and HD maps to support the different levels of driving automation. Today, many new vehicles include a range of advanced driver assistance systems (ADAS), such as predictive powertrain control (PPC) and intelligent speed assistance (ISA).

To deliver the most accurate information to the vehicle, we launched the TomTom ADAS Map in 2012. Already powering over one million cars on the road, the map supplies attributes about road gradient, curvature on road, traffic signs, speed restrictions, road curvature at junction, and lane at junction with an accuracy of several meters. With improved navigation guidance, speed controls and traffic sign and speeding warnings, ADAS Map data improves drivers' comfort, safety and builds trust.

When the vehicle can steer, accelerate and overtake other vehicles on its own, its level of automation sits between two and five. To achieve higher levels of autonomy, vehicles require a centimeter-level accurate, high-definition (HD) map.

This is where the TomTom HD Map comes in. It is a highly accurate representation of the road, featuring an array of attributes including lane models, traffic signs, road furniture and lane geometry. Supporting vehicle sensors, the map can tell the driver exactly where every road element is with extreme accuracy even in the worst weather conditions.

Using RoadDNA, TomTom has also solved the localization challenge, enabling the vehicle to precisely and accurately position itself on the road. All this complex and detailed map data is delivered via the AutoStream delivery system to ensure autonomous vehicles always have the most accurate and up-to-date map content.

The TomTom HD Map enables localization beyond GPS accuracy, helps with sensor perception and smoother path planning, all to increase driver safety and comfort.

ADASIS for ADAS and HD maps

Once the ADAS Map or HD Map is delivered through AutoStream, the data needs to be shared with the vehicle’s electronic control unit (ECU) to enable autonomous functions. The automotive industry has defined a standard protocol for map data information exchange, called ADAS interface specification (ADASIS). Since 2011, the second version of ADASIS has been implemented in millions of Level 2 cars and using TomTom ADAS Maps.

For higher levels of autonomous driving, cars rely on HD maps and the third version of ADASIS to handle the vast amounts of map data with lane-level accuracy. While the second ADASIS version only describes a road as a single line with attributes, the third version’s protocol can depict lane-level geometries of the road surface.

TomTom and Elektrobit’s partnership for autonomous driving

TomTom and Elektrobit have been partners since 2017 with the goal of achieving higher levels of autonomous driving. The collaboration involves integrating TomTom ADAS and HD Maps with the Elektrobit ADASIS horizon to enhance or enable autonomous tasks.

In 2018, we launched the industry-first reference implementation of ADASIS v3. This works as follows:

• 1. The map data predicts the upcoming driving path by considering the current vehicle position, driving conditions, and road data. A route imputed into the navigation system can also be imported.

• 2. It will use the HD Map data to create a map horizon. For example, the horizon will describe the different lane markings, curves and speed restrictions for the 5 kilometers ahead. The map data is then provided as an ADASIS-compliant data stream to all attached ADAS ECUs.

• 3. The autonomous driving system then fuses this map data with its sensor observations to build an environmental model. With this model, the autonomous vehicle can plan its next self-driving maneuver.

Safety considerations for autonomous driving with HD maps

With HD maps becoming an essential part of how vehicle sensors make sense of their environment, they are often required by carmakers to be subject to automotive safety integrity levels (ASIL) as defined by ISO 26262.

However, the nature of a map as a sensor implies using data that is at least a few minutes old. Due to the definitions in the ISO standard, ASIL cannot be assigned to map data.

As autonomous vehicles represent an emerging technology that will save lives, it is vital to carry out other safety considerations for HD maps. The streaming of the map data from the cloud source to the ADAS function needs to ensure data integrity. The implementation of safety concepts on different client platforms touch various safety aspects which must be considered in design decisions of ADASIS functions.

The future of autonomous driving is here with TomTom and Elektrobit

The near future  will continue to see the emergence and evolution of many more assisted and autonomous driving technologies. Autonomous driving will increase mobility, free time and reduce accidents.

For safe autonomous driving to become a reality, TomTom HD Maps are essential. The HD Map enables accurate localization, helps with sensor perception and path planning, all to improve driver safety and comfort. With this map data, the automated driving systems can anticipate the road ahead. Through our partnership with Elektrobit, we have implemented a practical solution to deliver HD Map data to the vehicle so it can carry out autonomous functions smoothly and safely.

For carmakers working towards higher levels of automation, TomTom HD Maps are the complete, already available solution for making autonomous driving a reality.