On-board processing device, vehicle control device, and self-position estimation method
An on-board processing device includes: a past map storage unit that stores a past generated map generated in the past; a self-map generation unit that generates a traveling map on the basis of sensor data acquired while traveling; a self-position estimation unit that estimates a self-position by collating the past generated map and the traveling map; and a data selection unit that selects data, to be used by the self-position estimation unit, from the traveling map on the basis of characteristics of data included in the traveling map.
1 . A vehicle control device comprising a processor configured to:
record a past generated map generated in the past and a traveling map generated based on sensor data acquired while a vehicle is traveling, the traveling map including first point group data, wherein the first point group data includes road surface point group data representing a road marking displayed on a road surface and high point group data representing an elevated feature having a height above the road surface;
execute first collation to collate past point group data included in the past generated map with the road surface point group data and collate the past point group data with the high point group data;
execute first self-position estimation to estimate a self-position of the vehicle based on a result of the first collation;
in response to a determination that the road surface point group data has higher accuracy compared with the high point group data, estimate the self-position of the vehicle based on a result of second collation to collate the past point group data with second point group data, wherein the second point group data is a subset of the road surface point group data, the subset selected from the past point group data and the first point group data; and
control, based on the estimated self-position of the vehicle, at least one of a steering device, a driving device, or a braking device of the vehicle.
2 . A vehicle control device comprising a processor configured to:
record i) a traveling map generated based on sensor data acquired while a vehicle is traveling and ii) travel status data including a first travel status at a time of generation of a past generated map, wherein the travel status data represents a vehicle operating condition and an environmental condition that affect sensor accuracy;
execute first self-position estimation to estimate a self-position of the vehicle based on a result of first collation to collate past point group data included in the past generated map with first point group data included in the traveling map, the first point group data including road surface point group data representing a road marking displayed on a road surface and high point group data representing an elevated feature having a height above the road surface;
in response to a determination that the road surface point group data has higher accuracy compared with the high point group data, select a subset of the road surface point group data, as second point group data, from the first point group data based on the first travel status at the time of generation of the past generated map and a second travel status at a time of generation of the traveling map;
estimate the self-position of the vehicle based on a result of second collation to collate the past point group data included in the past generated map with the second point group data; and
control, based on the estimated self-position of the vehicle, at least one of a steering device, a driving device, or a braking device of the vehicle.
3 . The vehicle control device according to claim 2 , wherein the processor is further configured to execute the second collation after the first collation.
4 . The vehicle control device according to claim 2 , wherein the processor is further configured to:
specify a type of data to be used for position estimation based on an estimation result of the self-position.
5 . The vehicle control device according to claim 4 , wherein the travel status data includes a current travel status.
6 . The vehicle control device according to claim 1 , wherein the processor is configured to: generate the traveling map converted into absolute coordinates estimated by a GNSS and odometry.
7 . The vehicle control device according to claim 6 , wherein connection is made via a communication line to a server that stores a map, the traveling map is transmitted to the server configured to be accessed by another vehicle, and the server is configured to receive a map generated by the other vehicle and use the map as the past generated map.
8 . The vehicle control device according to claim 1 , wherein the processor is further configured to output the estimated self-position to at least one of the steering device, the driving device, or the braking device of the vehicle.
9 . A self-position estimation method for estimating a self-position by an on-board processing device, the method comprising:
recording a past generated map generated in the past and a traveling map generated based on sensor data acquired while a vehicle is traveling, the traveling map including first point group data, wherein the first point group data includes road surface point group data representing a road marking displayed on a road surface and high point group data representing an elevated feature having a height above the road surface;
executing first collation to collate past point group data included in the past generated map with the road surface point group data and collate the past point group data with the high point group data;
executing first self-position estimation to estimate a self-position of the vehicle based on a result of the first collation;
in response to a determination that the road surface point group data has higher accuracy compared with the high point group data, estimating the self-position of the vehicle based on a result of second collation to collate the past point group data with second point group data, wherein the second point group data is a subset of the road surface point group data, the subset selected from the past point group data and the first point group data; and
controlling, based on the estimated self-position of the vehicle, at least one of a steering device, a driving device, or a braking device of the vehicle.