HD maps – the key to autonomous driving success?

By working with existing vehicle sensors, a HD map can extend a driverless car's line of sight beyond the next corner, writes Celeste Dooley

In-vehicle maps have seen great transformation from the earliest days of the automotive industry; from paper maps to digital solutions on a touch screen, the evolution of navigation has been a much-considered factor in automotive development. Now, technology companies are taking this one step further to support the growing trend of autonomous driving, by integrating a new age of high-definition (HD) maps into new vehicles.

HD maps enable vehicles to see beyond the driver’s field of view, providing an accurate representation of the road ahead and information on the surrounding environment. Though not limited to use only within autonomous vehicles, this technology will be particularly beneficial to vehicles with automated features. In fact, HD map information could be critical to their success.

Autonomy is not the limit

Although self-driving vehicles will not rely solely on HD maps, this technology can significantly enhance the functionality of autonomous driving features. “Lower levels of autonomy can function without an HD map, but it is not as safe or smooth,” Willem Strijbosch, Head of Autonomous Driving at TomTom, told M:bility. The company, which has been bulking out its capabilities in autonomous driving, stresses that GPS is no longer accurate enough for vehicles that are equipped with as low as Level 2 autonomous features. HD maps are not the solution, then, but they are a critical piece to the puzzle.

It does not matter if it is snowing or pouring down with rain, the map remains clear and increases the safety of these assistance systems

This is also true for vehicles on the market today, many of which feature low levels of automation provided through advanced driver assistance systems (ADAS). “The TomTom HD Map is not limited to autonomous driving, but can also be leveraged to fulfil a broad range of ADAS applications such as Predictive Powertrain Control, Highway Pilot, and Adaptive Cruise Control,” Strijbosch explained. “If there is very dense traffic ahead, you can ‘see’ through all of those cars, and understand what is around the corner or even two kilometres ahead of you. It does not matter if it is snowing or pouring down with rain, the map remains clear and increases the safety of these assistance systems.”

Building trust

Consumer trust is essential to the success of autonomous vehicles, and players are seeking ways to garner this trust. A recent study conducted by the American Automobile Association (AAA) found that only 20% of respondents would trust a self-driving car. One area causing concern for many consumers is the idea of sensor failure – if the car cannot ‘see’, can it drive?

Various passenger cars on sale today are equipped with sensors that can identify road markings, other vehicles and unexpected obstacles in the road. RoadDNA, a ‘suite of localisation attributes’ within TomTom’s HD mapping technology, acts as a level of redundancy if sensors are obstructed by dirt or poor weather conditions. This is a common issue today, with heavy rainfall often rendering camera sensors useless. Having the map as an additional layer of sensing could remove some of the doubts surrounding ADAS.

Improved road safety is generally presented as the greatest benefit of autonomous driving, with a significant reduction in human error behind the wheel. The additional safety that HD mapping technology brings is essential in order to achieve this vision, believes Strijbosch. But it is not just human error that is an issue today; the capabilities of some ADAS features also need to improve. He highlights recent events that have shown lapses in currently available highway pilot systems. In March 2018, one Tesla driver was killed when his Model S collided with a concrete lane divider on a Mountain View highway. With Autopilot engaged at the time, the system struggled to identify the correct trajectory and hit the barrier head on.

“Instances where these systems fail might have been prevented with a HD map because the vehicle would have known there was a curve coming, that there was a concrete barrier ahead, and that road markings were quite poorly visible,” suggested Strijbosch. “The vehicle’s sensors and HD map software all work in concert – they are each other’s redundancy.”

An interconnected system

Ideally, HD maps should be integrated with other connected features within a vehicle, explains Tomaso Grossi, Senior Product Marketer at TomTom Automotive. “We don’t see HD maps as standalone products. They don’t exist in a vacuum and must be used as part of the automated system in a vehicle,” he said. “We believe in a closed-loop system, whereby we produce the most accurate, robust and reliable maps in the cloud, deliver these systems to the car, and then leverage multiple sources – such as different types of vehicle sensors – to ensure this map is up-to-date, safe and matches reality.”

The vehicle’s sensors and HD map software all work in concert – they are each other’s redundancy

To further improve its HD maps, TomTom is currently utilising observations from a variety of sensors, including cameras, within the vehicle. “All cars have a camera,” Strijbosch pointed out. Road infrastructure, such as traffic signs, can be recognised by the vehicle’s cameras. This data is then fed into the RoadDNA software, and can be compared against the HD map data. If multiple traffic signs can be seen, this should be enough for the car to determine its exact location. “It is a great localisation attribute, which utilises the vehicle’s existing cameras,” he explained.

The goal is to improve an autonomous vehicle’s awareness and to provide precise information on where it is on the road, often referred to as ‘contextual awareness.’ Looking ahead, Strijbosch affirms that Level 3 and Level 4 autonomous vehicles must have HD mapping technology – it is not up for debate, he suggests: “Level 2 vehicles are on the road today without a HD map, but all of the car manufacturers are looking to integrate these maps to make their systems smoother, and ultimately, safer.”

TomTom is not the only company exploring the benefits of HD mapping. Companies such as Nvidia, Vexcel, and HERE Technologies – Nokia’s spun-off mapping unit that was bought by Audi, BMW and Daimler in 2015 – are also developing similar offerings. In China, NavInfo has tasked itself with charting domestic roadways in HD for autonomous vehicles. The faith that companies are showing in this technology is demonstrative of its potential to advance the safety of automated driving functions, right from low-level ADAS features up to the driverless vehicle.

Turn-by-turn signals afforded by traditional GPS navigation systems will no longer cut it in future when the car is in control. By enhancing navigation into a digitalised, HD platform, connected and autonomous features can be confidently deployed and adopted in the knowledge that there are fail-safe systems in place to support them.

This article appeared in the Q4 2018 issue of M:bility | Magazine. Follow this link to download the full issue

Close
Close