Mitsubishi Electric develops technologies for automated mapping and extraction of transitions in mapping landscape for high-precision 3D maps
Mitsubishi Electric Corporation has developed two new technologies to support the creation and maintenance of high-precision 3D maps required for autonomous driving (earlier post): AI-based automated mapping; and the extraction of transitions in mapping landscapes.
The technologies are based on the company’s own Mobile Mapping System (MMS) (earlier post) for the creation of highly precise three-dimensional maps that provide static information of roads and surrounding objects. Both technologies will be exhibited for the first time at CeBIT 2017 in Hannover, Germany from 20-24 March 2017.
Mitsubishi Electric aims to contribute to the early implementation of maps that offer constantly updated dynamic information, such as traffic signals and information about surrounding vehicles etc., for safe, highly precise autonomous driving.
The MMS—a highly accurate measuring system using car-mounted GPS antennas, laser scanners and cameras—gathers 3-D positioning data of road surfaces and roadside features to an absolute accuracy of 4 inches (10 cm), allowing the creation of comprehensive 3D maps to the level of accuracy needed to support autonomous driving.
Automated Mapping Technology. The automated mapping technology uses AI to create precise, accurate three-dimensional maps quickly. Only necessary information, such as road markings and traffic signs, is extracted from laser-point clouds and camera data measured and collected by MMS.
Mitsubishi Electric’s MMS provides 3D positional information of roads and roadside structures with an absolute precision within 10cm or less, which is collected via a system consisting of laser scanners, cameras and GPS antennas, while driving. AI improves the precision of extraction and recognition of the only data necessary, resulting in some 10 times faster map creation compared to industry-standard manual creation. The system also costs less than conventional methods.
Technology for Extraction of Transitions in Mapping Landscape. Mitsubishi Electric is using its difference extraction technology for earlier establishment of the dynamic map itself and more efficient updating and maintenance at a faster pace.
By automatically extracting characteristic points of past data and the latest laser-point cloud data measured with MMS, the difference extraction technology is able to distinguish differences and changes where characteristic points do not match. With this technology, the maintenance of dynamic maps and the updating of precise 3D maps can be accomplished much faster by automatic extraction of only the points that has changed, compared to updating the entire map each time.
Looking ahead, Mitsubishi Electric plans to sell software utilizing this automated mapping and difference extraction technologies to map publishers including Dynamic Map Planning Corporation this coming October. The software will be used for the creation of highly precise 3D maps of expressways in Japan.
Background. Automated driving in Japan is expected to evolve from advanced driver assistance systems (ADAS) to automatic-driving level 3 (conditional autonomous operation) between 2019 and 2020, creating further demand for related systems.
Automatic driving systems will require combinations of in-vehicle sensors as well as dynamic maps; one of the biggest challenges will be to keep the map information constantly up to date. Mitsubishi Electric’s new technologies for automated-mapping and extraction of transitions in mapping landscape create and renew precise 3D maps faster and efficiently, and therefore are expected to serve as the core technologies of dynamic map creation.