The world is taking a huge step towards an autonomous future, and as this revolution comes, vehicles will require a new generation highly accurate and realistic maps to ensure autonomous driving is safer, cleaner and can bring our vision of a less congested world to a reality.
To make this a reality, autonomous vehicles will rely on artificial intelligence, sensors and digital maps. These are the eyes and ears of the car and maps are one of the most important innovations to make sense of the various info streams, from navigation and points of interest to live weather and traffic plus behavioural data.
High-definition maps will help in moving towards a new standard of safety for autonomous driving. TomTom highlighted that 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. The company launched the TomTom ADAS Map in 2012. The software is 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 speed warnings, ADAS Map data improves drivers’ comfort, safety and builds trust.
Swift has also been developing Swift Navigation lane-level positioning production solution which was designed for autonomy and is already built to scale for automotive. The receiver-agnostic Starling positioning engine easily integrates with the automotive sensor suite and pulls corrections from Skylark to deliver absolute positioning for safety-critical autonomous vehicle applications. Swift combines the signals from the GNSS, including GPS and the ground base stations. Its solutions use a mathematical model to correct the errors created from the satellites, resulting in a high-precision positioning of the vehicle in motion.
Mercedes Benz’s DRIVE pilot is also a key player in the development of mapping technology in autonomous vehicles. The company has integrated HERE technology into its mapping platform which is said to be capable of “seeing around corners”. The DRIVE pilot can control the speed and distance between vehicles which enables the car to drive safely between lanes. Mercedes gave a fantastic talk at CES talking about how autonomous vehicles powered by HD maps are only a matter of time.
HERE technologies have developed a map solution that includes HD lane, HD localization, and road models. By combining the semantic data from satellite, cellular, Wi-Fi, and sensor technologies, an AV employing the HERE technology can correctly interpret road signs and poles, mirroring what a human driver could do.
Lastly, NVIDIA has also developed a multilayered mapping system called DRIVE Map. This platform consists of localised road signs, including lane dividers, road markings, road boundaries, traffic lights and signals. In the last six years, the company has been building multiple localised layers of data with cameras, radar, lidar, and GNSS4.
There are also several challenges that are involved when building these maps. There are huge project costs involved as there is a high need for manual verification and requirements for fresh maps and data sourcing. Furthermore, national and international regulatory permissions means that lots of approvals are required before driverless vehicles can be on our roads. Controlling the quality of maps is also a challenge as the road environments are quite complex and are constantly changing.
Improving accuracy will forever be essential for autonomous vehicles as we aim to provide safe and accurate routes for passengers. Many companies are now striving to achieve high-quality HD mapping to ensure that vehicles are on the road as early as possible.
As of today, many businesses are investing into autonomous driving and mapping technologies, and in turn, they will only continue to evolve and improve.
