Skip to main content

Toyota demos HD maps for Tokyo AVs

Toyota's Research Institute-Advanced Development has demonstrated high definition (HD) maps for autonomous vehicles (AVs) for surface roads in Japan with a relative accuracy of less than 50cm.
By Ben Spencer March 31, 2020 Read time: 2 mins
Toyota demos HD maps for AVs for surface roads in Japan (© Rui Baião | Dreamstime.com)

Toyota is hoping to use the results to shorten the delay in updating HD maps for AVs, expand map coverage and reduce maintenance costs.
 
The company collaborated with space infrastructure company Maxar Technologies and IT services provider NTT Data to build the maps using commercial satellite imagery.
 
The demonstration allowed the partners to automatically extract the required map information by analysing, removing and correcting non-map image pixels such as cars and shadows due to the inclination of buildings in satellite imagery. Maps were created within the 23 wards of Tokyo as well as six unnamed cities in the US and Europe.

A collaboration with road intelligence firm Carmera showcased how to make maps using consumer-grade vehicle cameras. Both parties used dashcam drive recorders to detect and place road features such as lane markings, traffic signals and signs within the 23 wards of Tokyo and two unnamed cities in the US state of Michigan.

In a separate initiative, Toyota showed how lane markings necessary for AVs could be updated in near real-time on TomTom's HD map. This was achieved by converting vehicle data into TomTom's cloud-based transactional mapmaking platform, Toyota says.
 
Additionally, Toyota worked with Here Technologies to correct the positional errors in its vehicle data. Here created surface road maps and ingested data into its platform and automatically generated HD maps including lane level information, the company adds.

 

Related Content

  • January 18, 2012
    Inertial sensors dramatically improve GNSS for ITS applications
    Phil Harris, Thales UK, on how fused sensor data can significantly enhance GNSS-based positioning systems' performance in urban areas. Global Navigation Satellite System (GNSS)-based positioning is unique among available positioning technology due to its universal coverage and low equipment cost. By measuring the distances between an unknown position (such as a vehicle), and at least three known positions (GPS satellites), the unknown position can be calculated in three dimensions (latitude, longitude, and
  • September 13, 2019
    TomTom enters partnership to update HD Map
    TomTom has partnered with Hella Algaia, a supplier of computer vision software, to update its high definition (HD) map in real-time using crowdsourced data from vehicles.
  • November 10, 2015
    User-based insurance joins the battle for big data
    User-based insurance is blazing a trail others would like to follow and is also discovering the challenges. The ITS sector needs to keep a very careful eye on the automotive industry: “There’s a war going on in the connected car space creating richer datasets than we ever imagined possible” says Paul Stacy, research and development director of Wunelli, part of the LexisNexis group. The car makers have gone way beyond infotainment, unlocking huge amounts of data in the process … facts and figures which the i
  • June 23, 2020
    Here: AI has place in ‘privacy by design’
    Artificial intelligence may improve traffic in cities and keep location data private, but Here Technologies shows that it only takes four points of anonymous data to predict your identity.