Mitsubishi Electric is accelerating dynamic road mapping

Mitsubishi Electric wants to propel the autonomous driving from the navigation side and uses landscape mapping for artificial intelligence (AI) and its mobile mapping system (MMS). The goal is three-dimensional, dynamic maps.

Autonomous vehicles must be highly precise.
Image: Mitsubishi Electric

According to the Japanese company, it is developing a range of technologies for the automated creation of road maps and also includes applications that incorporate the modified elements in a landscape mapping. The applications are based on artificial intelligence (CI) and the mobile mapping system developed by Mitsubishi Electric (MMS), which allows the development of extremely precise three-dimensional maps. They provide static information about roads and surrounding objects - and thus provide the basis for dynamic maps, which are classified as indispensable for autonomous driving. It is about continuously updated, dynamic information such as traffic lights and data about other vehicles on the road.
Automated mapping technology uses AI to quickly and accurately create three-dimensional road maps. In doing so, the solution extracts only the information from the laser point clouds and comrades measured and collected by the MMS. This includes, for example, traffic signs and road markings. The MMS from Mitsubishi Electric provides 3D positioning information on roads and buildings with an accuracy of ten centimeters or less. These are recorded via a system consisting of laser scanners, cameras and GPS antennas while driving. AI enhances the extraction and recognition of the necessary data. 
"This allows maps to be developed up to ten times faster than conventional manual creation," says Mitsubishi Electric.

Mitsubishi Electric uses a technology for the development of dynamic road maps, which only records the changes that have occurred since the last data collection. This allows faster and more efficient updating and maintenance of the cards. The technology automatically extracts the characteristic points of existing data, combines them with the latest laser point data that is measured by MMS, thus recognizing differences and changes. Thanks to this technology, dynamic maps can be better managed and accurate 3D road maps can be updated faster as only the points that have changed are revised. So far the maps have been completely updated with every change.
Mitsubishi Electric plans to distribute the software for automated map production as well as the technologies for processing the changed road data to card companies such as the Dynamic Map Planning Corporation from October. The application is used to develop extremely precise 3D maps of Japanese motorways.
Between 2019 and 2020, automated driving in Japan will evolve from advanced driver assistance systems (ADAS) towards level 3 automated driving (autonomous operation under certain conditions) - thus generating additional demand for appropriate systems. Automated driving systems require a combination of sensors within the vehicle as well as dynamic road maps. The biggest challenge: the information of these cards must always be up-to-date.