We hear a lot of hype about autonomous cars, but it isn’t often that we hear about what goes on behind the scenes. I’m specifically talking about how these self-driving cars happen to know where they are going, the local traffic laws, road signs, and dividing lines. Your common GPS unit can show you a reasonably accurate map of the road, but very few can break it down into an accurate display of lanes, and none – that I’m aware of – display actual traffic signs. Up until this point, map data for autonomous vehicles is provided by other vehicles that are equipped with laser scanners. Data collected eventually has information like dividing lines and road signs manually inserted. This method is effective, but is expensive, subjected to errors, and isn’t updated frequently. Toyota is about the change the game, however, with a new system that will offer higher precision and won’t require as much manual editing.

Toyota’s new system will work somewhat like the current system used in Google’s self-driving cars. Cameras are attached to regular production vehicles, record the road, road signs, and various aspects of each road. In combination with GPS information, this information is uploaded to a special data center that automatically compiles all of the information in usable, high-precision map data. Toyota has noted that there is a higher potential for error with camera-based systems in comparison to current technology, but has stated that the margin of error can be dramatically reduced by combining data from multiple vehicles.

This technology is set to debut at the Consumer Electronics Show in Las Vegas between January 6th and January 9th, 2016. Toyota’s vision is that this technology will be a primary element that will make it possible to have self-driving vehicles by the end of the decade. At the start of things, this technology will be used primarily to map highway roads, but it will eventually evolve to map out ordinary roads as well. In a perfect world, Toyota hopes to collaborate with other map makers and encourage the widespread use of the technology.

Continue reading for the full story.

Why it matters

Toyota Will Present New Map Generation System At 2016 CES
- image 660182

I’m sure we all remember the problems that came about by early GPS technology. There was nothing worse than relying on a system that was inaccurate and often led you to drive in circles. Even worse, sometimes it would take you into parking lots it mistook as a road, and lets not even touch on the concept of road closures due to construction. That kind of thing is why this technology is so important when it comes to reliable self-driving cars. Self-driving cars will ultimately prove to be much safer, but we’re approaching the technology at a slug’s crawl for a reason – if the technology isn’t flawless, it will do more harm than good.

For autonomous cars to be safe and useable by the masses, the technology must be perfected, and the data they rely on has to be accurate. This technology is a step in that direction. Considering the camera based systems will be installed on production vehicles, I wouldn’t doubt it if eventually every car comes equipped with the camera technology and connectivity to the cloud. As the masses go about their everyday business, new data will be uploaded – ultimately allowing on-the-go updates to self-driving cars in regards to road conditions, changes on the roadway and the like. I see it turning into a system where every car on the road is constantly uplink to a massive server that takes and supplies new information. There will always be those that question motives, and if this technology does evolve into that, it will surely raise the issue of privacy and tracking. We’ll leave that for a future debate, though.

Press Release

To aid the safe implementation of automated driving, Toyota is developing a high-precision map generation system that will use data from on-board cameras and GPS devices installed in production vehicles. The new system will go on display at CES (Consumer Electronics Show) 2016 in Las Vegas, which will run from January 6 through 9.

Toyota Will Present New Map Generation System At 2016 CES
- image 660183

Toyota’s new system uses camera-equipped production vehicles to gather road images and vehicle positional information. This information is sent to data centers, where it is automatically pieced together, corrected and updated to generate high precision road maps that cover a wide area.

An understanding of road layouts and traffic rules (including speed limits and various road signs) is essential for the successful implementation of automated driving technologies. Additionally, high precision measurement of positional information requires the collection of information on dividing lines, curbs, and other road characteristics.

Until now, map data for automated driving purposes has been generated using specially-built vehicles equipped with three-dimensional laser scanners. The vehicles are driven through urban areas and on highways, and data is collected and manually edited to incorporate information such as dividing lines and road signs. Due to the infrequent nature of data collection, maps generated in this manner are seldom updated, limiting their usefulness. Additionally, this represents a relatively cost-intensive method of gathering data, due to the need to manually input specific types of data.

Toyota Will Present New Map Generation System At 2016 CES
- image 660184

Toyota’s newly developed system uses automated cloud-based spatial information generation technology (developed by Toyota Central R&D Labs., Inc.) to generate high precision road image data from the databanks and GPS devices of designated user vehicles. While a system relying on cameras and GPS in this manner has a higher probability of error than a system using three-dimensional laser scanners, positional errors can be mitigated using image matching technologies that integrate and correct road image data collected from multiple vehicles, as well as high precision trajectory estimation technologies. This restricts the system’s margin error to a maximum of 5 cm on straight roads. By utilizing production vehicles and existing infrastructure to collect information, this data can be updated in real time. Furthermore, the system can be implemented and scaled up at a relatively low cost.

To support the spread of automated driving technologies, Toyota plans to include this system as a core element in automated driving vehicles that will be made available in production vehicles by around 2020. While initial use of the system is expected to be limited to expressways, future development goals include expanding functionality to cover ordinary roads and assist in hazard avoidance. Toyota will also seek to collaborate with mapmakers, with the goal of encouraging the use of high precision map data in services offered by both the public and private sectors.

In October 2015, Toyota introduced the Mobility Teammate Concept, which is part of the company’s approach to embracing automated driving technologies while keeping fun at the center of the driving experience. To that end, the Mobility Teammate Concept envisages a driver-car relationship based on a shared purpose?somewhat like a relationship between close friends who alternately watch over each other and help each other out. Toyota will continue to develop of technologies that aid the spread of automated driving technologies, with the aim of realizing a society where mobility is synonymous with safety, efficiency, and freedom.

View the full press release Hide press release
Press release
What do you think?
Show Comments
Car Finder:
Related Manufacturers