Japan’s Toyota develops map generation system for self-driving cars

Japan’s Toyota develops map generation system for self-driving cars


Japan: Toyota is developing a high-precision map generation system for automated cars. This system will use data from on-board cameras and GPS devices in the vehicle to gather road images and vehicle positional information. The collected information will then be sent to data centers to be corrected and updated for the generation of high-precision road maps. The Japanese carmaker will display the new system at CES (Consumer Electronics Show) 2016 in Las Vegas, from January 6-9.

Until now, map data for automated driving has been generated using specially-built vehicles equipped with three-dimensional laser scanners. The vehicles are driven through urban areas and on highways, and data is collected and manually edited to incorporate information such as dividing lines and road signs. Due to the infrequent nature of data collection, maps generated in this manner are seldom updated, limiting their usefulness. Additionally, this represents a relatively cost-intensive method of gathering data, due to the need to manually input specific types of data.

Toyota's newly developed system uses automated cloud-based spatial information generation technology, which has been developed by Toyota Central R&D Labs. While a system relying on cameras and GPS in this manner has a higher probability of error than a system using three-dimensional laser scanners, positional errors can be mitigated using image matching technologies that integrate and correct road image data collected from multiple vehicles, as well as high precision trajectory estimation technologies. This restricts the system's margin error to a maximum of 5 cm on straight roads. By utilizing production vehicles and existing infrastructure to collect information, this data can be updated in real time. Furthermore, the system can be implemented and scaled up at a relatively low cost.

Source: Toyota