Why autonomous vehicles will fail without the accurate detection of precise positioning

With speed limiters being added to new vehicles made in Europe as part of new continent-wide plans to reduce road traffic accidents, the role of accurate positioning is more vital than ever in reducing accidents and the promotion of autonomous vehicles. Dr Ramsey Faragher, Founder & CTO of Focal Point Positioning tells us why.

The new Vehicle General Safety Regulation has come into force. It introduces a range of mandatory advanced driver assistance systems to improve road safety and establishes the legal framework for the approval of automated and fully driverless vehicles in the EU. The new safety measures will help to better protect passengers, pedestrians and cyclists across the EU, expectedly saving over 25,000 lives and avoid at least 140,000 serious injuries by 2038. The 2019/2044 regulation also mandates all new cars that have already launched be fitted with an Intelligent Speed Assist (ISA) by 7 July 2024.

The General Safety Regulation is effectively the legal framework for automated and connected vehicles, in addition to the technical rules for the approval of fully driverless vehicles. The aim of the General Safety Regulation is to increase public trust, boost innovation and improve the competitiveness of Europe's car industry.

Currently, no decision has been made by the UK government to follow in the footsteps of the EU to introduce Intelligent Speed Assistance (ISA) and make it a legal requirement for manufacturers to include them.

However, since most cars made in Europe are sold in the UK too, just with right-hand drive, the tech will be widespread here as well. Pressure is mounting from the Society of Motor Manufacturers and Traders (SSMT), leading car brands and Euro NCAP Testing to have uniformity across the continent, but nothing has been decided at this point.

The primary motivation behind the introduction in the EU has been safety of all road users.

The European Transport Safety Council announced that the technology will reduce road collisions by 30% and deaths by 20%. It is also part of the EU’s goal to have zero road deaths by 2050.

ISA is designed to inform the driver when they are speeding and reduce the speed of the vehicle. The car determines the current speed limit by either reading road signs with a camera, or by determining the speed limit using GPS and a stored database of roads. ISA then notifies a speeding driver using visual cues, audio cues or by vibrating the pedals under the driver’s feet , warning the driver that they have exceeded the speed limit. If the speed is not subsequently reduced the system can reduce the engine power to slow the vehicle.

The system sounds hugely beneficial, but in practise there will be some important issues to overcome.

Machine vision is generally not as reliable as human vision when context and complex environments are important. For example small speed restriction signs on the back of trucks, indicating their maximum speed, could be misread by ISA cameras as the current road speed. Similarly, GPS positioning accuracy can be poor in urban environments where signals are blocked and reflected, leading to an ISA system believing it is on a 20 mph side road when it is really on a 70 mph dual carriageway.

Solutions to these issues lie in improvements to these technologies. Machine vision systems will need to extend beyond simple number recognition and include the wide context of the scene:

• Is the speed sign mounted to and moving with another vehicle?
• Is the speed sign in the immediate proximity of the current carriageway, or is it actually connected to a neighbouring, or branching one?
• And is the GPS receiver returning a high or low integrity score?
• What is the error associated with the position fix provided?
• Is this region urban and known to be low in GPS positioning accuracy?

Ideally the two systems should be combined with a third, perhaps the detection and monitoring of the speeds of the surrounding vehicles, to provide a voting system or an aggregate estimate of the speed limit of the carriageway in use.

What causes GPS inaccuracies?

Satellite positioning (also known as GPS or GNSS) works by using timestamps broadcast by satellites. GNSS receivers use timestamps from at least 4 satellites, combined with the known satellite position in space, to calculate the receiver’s position on earth. This works perfectly when the satellite signal is unobstructed and the direct Line Of Sight (LOS) is detected.

However, most GNSS-enabled devices these days are used in more busy cities, where satellite signals can be easily reflected or obstructed by objects such as buildings, vehicles, landmasses and even vegetation. When receivers pick up a reflected or Non Line of Sight (NLOS) signal, the timing message will be older than it should be (echos always arrive late) and so the subsequent estimation of distance to the satellite will be too long, resulting in an inaccurate positioning fix. Even if the line of sight signal is available, any reflected or blocked copies can interfere with it when they are all picked up by the receiver together, corrupting the true measurement, making it look either early or late through distortion of the signal. This problem, known as multipath interference, is especially problematic in built up areas.

Multipath interference and NLOS signals can result in positioning fixes in cities being wrong by over tens of metres, which can mean catastrophic results for drivers whose vehicle safety with ISA is dependent on accurate positioning.

Whilst the imperative to reduce incidents is sound, speed limiters will create potentially dangerous situations when they return an incorrect limit. To provide their intended benefit they will need to be reliable and trusted by their users.

You can find this article published in Forbes.