Toyota enters partnership to build HD maps for AVs from space

Toyota Research Institute-Advanced Development (TRI-AD), technology company Maxar Technologies and NTT Data are working together to build high-definition (HD) maps for autonomous vehicles (AV) using satellite imagery. TRI-AD carried out an analysis, saying that current HD maps cover less than 1% of the global road network and there is a need to broaden the coverage of urban areas and local roads before AVs can become a mainstream mobility technology. A HD map created from satellite imagery would all
May 3, 2019 Read time: 2 mins
1686 Toyota Research Institute-Advanced Development (TRI-AD), technology company Maxar Technologies and NTT Data are working together to build high-definition (HD) maps for autonomous vehicles (AV) using satellite imagery.


TRI-AD carried out an analysis, saying that current HD maps cover less than 1% of the global road network and there is a need to broaden the coverage of urban areas and local roads before AVs can become a mainstream mobility technology.

A HD map created from satellite imagery would allow the driving software to compare multiple data sources and signal the car to take action to stay safe, the company adds.

Utilising Maxar’s Geospatial Big Data Platform, imagery from the company’s satellite imagery library will be fed into NTT Data’s specialised algorithms using artificial intelligence to extract information to generate the road network. TRI-AD will then make HD maps available for delivery from its cloud into Toyota test vehicles.

Mandali Khalesi, vice president of automated driving at TRI-AD, says advances in electronics and aerospace engineering are leading to higher resolutions and more frequent updates of global imagery from space-based assets.

“Additionally, machine learning is helping automate the discovery and integration of semantic relationships between road elements within image data,” Khalesi adds.

NTT Data, an IT services provider, will use its artificial intelligence and enhanced image-processing resources to expand the coverage of HD maps.

Katsuichi Sonoda, vice president and head of NTT Data’s social infrastructure solution sector, says: “In the future, we hope to map worldwide road networks from space using our enhanced image-processing expertise.”

Location Based Systems

Related Content

  • Here Technologies opens self-driving car R&D site in Colorado
    April 13, 2018
    Global provider of high-definition (HD) maps for autonomous vehicles (AVs) Here Technologies has opened a research and development facility in Boulder, Colorado. The centre will collaborate with professionals in geospatial engineering, machine learning and data science to develop processes that allow the company’s HD Live Map to self-heal. This process uses crowdsourced data from live car sensors to validate and update the HD map to help maintain its accuracy. Here’s HD map intends to provide overall
    Read More
  • Autonomous vehicle accuracy mapping from TomTom
    October 8, 2015
    Pride of place on satellite navigation pioneer TomTom’s stand is very high resolution 3D mapping, initially for Germany, which it says provides the 10cm accuracy necessary for highly automated vehicles. Its mainstream mapping is also high definition meaning the image can be used on any size of screen – as visitors can see.
    Read More
  • CES 2019 says hello to the future
    February 20, 2019
    The launch of the latest gadgets has made the Consumer Electronics Show into tech heaven for geeks worldwide – but there is a serious ITS component, too. Ben Spencer braves the bright lights of Las Vegas to find out more The Consumer Electronics Show (CES) has been the showcase for some of the world’s most iconic gadgets – from VCRs to the Commodore 64, and from the camcorder to the launch of HDTV. This has made CES a mecca for tech heads all over the world since it began in the 1960s, but these days it
    Read More
  • Aimsun enters partnership to develop tool for managing mixed-autonomy traffic
    January 15, 2019
    Aimsun has partnered with UC Berkeley’s Institute of Transportation Studies to develop Flow, a tool for managing large-scale traffic systems where human-driven and autonomous vehicles (AVs) operate together. Flow offers a suite of pre-built traffic scenarios and is now integrated with Aimsun Next mobility modelling software. The open source architecture knits together microsimulation tools with deep reinforcement learning libraries in the cloud. Launched last September, Flow allows users to build and
    Read More

Highlighted Content