Skip to main content

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.”

For more information on companies in this article

Related Content

  • Dutch are most ready for AVs - but bikes are an obstacle, says KPMG
    February 14, 2019
    The Netherlands is the number one country in terms of readiness to deploy autonomous vehicles (AVs) – except for one small problem: bicycles. People on two wheels - in this notoriously bike-friendly country - pose a problem for the deployment of AVs in built-up areas, according to research by KPMG. “We have a lot of bicycles,” says Stijn de Groen, manager digital advisory, automotive, at KPMG in the Netherlands. “In urban, crowded areas it will be very difficult to start autonomous driving.” Leavin
  • EdgeVis removes bandwidth barriers to mobile streamed video
    October 26, 2017
    A new generation of video compression can lower transmission costs of data and make streaming from mobile and body-worn cameras a reality, as Colin Sowman discovers. Bandwidth limitations have long been the bottleneck restricting the expanded use of video streaming for ITS, monitoring and surveillance purposes. Recent years have seen this countered to some degree by the introduction of ‘edge processing’ whereby ANPR, incident detection and other image processing is moved into (or close to) the camera, so
  • IBTTA: industry must commit to trust and accountability
    August 23, 2018
    Without a commitment to trust and accountability, the modern road tolling industry would not have the bedrock which it requires – and which customers demand, says IBTTA’s Bill Cramer When Tim Stewart, executive director of Colorado’s E-470 Public Highway Authority, settled on ‘trust and accountability’ as the themes for his year as IBTTA president, it was a very deliberate choice. Stewart was looking for language that would help deliver the global tolling industry’s message of service excellence to cust
  • Mobileye launches new mapping technology, integrates with GM and Volkswagen
    March 17, 2016
    Both General Motors and Volkswagen are to incorporate Mobileye’s new road experience management (REM) mapping technology into their vehicles. REM uses crowd-sourced real-time data for precise localisation and high-definition lane data that forms an important layer of information for autonomous driving. The software, based on that running on Mobileye's EyeQ processing platforms, extracts landmarks and roadway information at extremely low bandwidths – using approximately 10kb/km.