Toyota Mapping Technology Will Help the Introduction of Automated Driving

A better understanding of road signs, markings and layouts is crucial for the safe implementation of automated driving, but this is definitely not an easy task for those in the self-driving industry. Toyota plans to tackle this problem through mapping technology that relies on crowdsourcing to deliver maps that are constantly updated.

This is definitely important and exciting news for the connected car industry and the future of automated driving. Here’s what we know about Toyota’s new map generation system so far:

Collecting Data to Aid Automated Driving

Gathering road information as a way to assist self-driving cars on the road is not something new.

Big players such as Google and Apple have spent big bucks on small fleets of cars that drive around collecting data that is used to create digital maps to help self-driving cars find their way on the road.

Another example that comes to mind is Tesla Motors. Unlike Google or Apple, Tesla’s approach involves harnessing the power of the cloud to map roads, then share that information wirelessly with every Tesla ever built.

Most of the previous systems that collected data for automated driving purposes used specially-built vehicles equipped with three-dimensional laser scanners that were driven through urban areas and on highways. The big disadvantage with these types of systems is that the data collected by vehicles is edited manually to incorporate important road information such as dividing lines and road signs.

It’s slow and complicated.

How Is Toyota’s Mapping Technology Different?

Well, Toyota’s plan is to make the whole process easier and more effective with “designated user vehicles”.

Its mapping technology uses cameras embedded in the vehicles and GPS devices installed in production vehicles to gather road images and vehicle positional information. The data regarding road conditions will then be sent to data-processing centers that will use it to improve mapping for self-driving cars.

There is no denying that the data collected by cameras and the GPS is not as accurate as the data gathered through laser scanners. However, Toyota doesn’t necessarily see that as a major disadvantage. As long as there are enough cars on the road transmitting data, Toyota is confident it can piece together enough images to triangulate what’s really out there.

What Are Its Biggest Strengths?

One of the biggest advantages of the mapping technology presented by the Japanese manufacturer is that it will deliver real-time updates by using production vehicles and existing infrastructure to collect information. This results in two important benefits:

  • Reduced costs – By making use of existing infrastructure, Toyota’s system can can be implemented at a relatively low cost.
  • Hazard avoidance – Safety remains a concern when it comes to putting self-driving cars on the road. With Toyota’s system, a vehicle will be able to not only take care of their drivers, but also warn other vehicles that are on the same route about possible dangers ahead by using its cloud-based image tech.     

Toyota’s mapping technology is also supposed to be pretty accurate, with a maximum margin error of 5 cm on straight roads.

Power Lies in Numbers

Toyota’s idea isn’t going to work with just one car out on the road collecting data, but with a whole fleet of vehicles doing double-duty as map generators. However, this is a whole different story. The more vehicles, the more detailed and accurate the maps will become.

Just think about it. If everybody’s car would act as a map generator, the information gathered will be constantly updated, which is a huge step forward for the connected car industry.

Toyota’s plan is to have these autonomous cars ready to go by around 2020.

Until then, I’m curious to know what your opinion on Toyota’s proposed solution to aid the safe implementation of automated driving is. Does it have potential or not? And what do you think its major drawbacks are?

Please let me know in the comment section below.

Philipp Kandal