Japanese IT services provider NTT Data is partnering with the Toyota Research Institute-Advanced Development (TRI-AD) and Maxar Technologies to work on high-definition maps for AVs. The project is initially a proof of concept to see if satellite imagery can be used for the purpose.
The partnership is part of TRI-AD’s open software platform concept Automated Mapping Platform (AMP) and will help make AV technology more scalable. According to TRI-AD’s analysis, only 1% of the global road network is represented in HD maps. However, both urban areas and local roads need to be mapped to ensure AV safety.
In this proof of concept, the three companies will work together to process satellite imagery into vehicle-friendly HD maps. Using Maxar’s cloud-based Geospatial Big Data platform (GBDX) the group will feed optical satellite imagery from Maxar’s library into NTT Data’s specialized algorithms. These algorithms use AI to extract the necessary information to generate the detailed road network.
TRI-AD will then run the HD maps in Toyota test vehicles, using its cloud. The project initially focuses on just the Tokyo metropolitan region, with scope to be expanded later.
Mandali Khalesi, vice president for automated driving at TRI-AD, said, “Recent 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. We’re excited to collaborate with Maxar and NTT Data to revolutionize automated driving mobility for all.”
Katsuichi Sonoda, vice president and head of NTT Data’s social infrastructure solution sector, said, “We have been fully engaged in the satellite-imaging business for 20 years, providing our AW3D-branded 3D maps on a global short-delivery basis.
“In this new project, we will use NTT Data’s AI and enhanced image-processing expertise to expand the coverage of high-definition maps on a fast, scalable and cost-effective basis. In the future, we hope to map worldwide road networks from space using our enhanced image-processing expertise.”
Interested in HD mapping for AVs? Make sure to catch the Vision – LiDAR, Sensors & Mapping Technology session at the Autonomous Vehicle Test & Development Symposium, which takes place at Autonomous Vehicle Technology Expo in Stuttgart on May 21-23.