Self-position estimation device

A self-position estimation device equipped to a vehicle, the self-position estimation device comprising:

• a vehicle-mounted camera capturing an image of a periphery of the vehicle;
• a vehicle state quantity sensor detecting a state quantity of the vehicle;
• a satellite positioning acquisition unit acquiring latitude and longitude of a position of the vehicle from a satellite system;
• a map data storage storing map data that defines a map in which a road is expressed by a link and a node;
• and
• a position estimation unit estimating a self-position of the vehicle on the map, as an estimation position, based on the image captured by the vehicle-mounted camera, the state quantity, the latitude and longitude, and the map data, respectively;
• wherein the position estimation unit includes:
• a lane quantity change determiner recognizing a road section in which a lane quantity increases or decreases based on a sensing of the vehicle-mounted camera;
• and
• a position corrector correcting the estimation position of the vehicle estimated by the position estimation unit based on the map data by setting a weighting of the estimation position of the vehicle estimated based on the map data smaller in response to a recognition of the road section in which the lane quantity increases or decreases compared with a case where the road section in which the lane quantity increases or decreases is not recognized.

A self-position estimation device equipped to a vehicle and estimating a position of the vehicle, the self-position estimation device comprising:

• a vehicle-mounted camera capturing an image of a periphery of the vehicle;
• a vehicle state quantity sensor detecting a state quantity of the vehicle, the state quantity of the vehicle including a vehicle speed;
• a receiver receiving position information indicating a position of the vehicle from a satellite system;
• a map data storage storing map data that defines a map in which a road is expressed by a link and a node;
• and
• a processor, by executing a program stored in a non-transitory computer readable medium, configured to:
• estimate a self-position of the vehicle on the map, as an estimation position, based on the image captured by the vehicle-mounted camera, the state quantity of the vehicle, the position information of the vehicle from the satellite system, and the map data, respectively;
• recognize a road section in which a lane quantity increases or decreases based on the image captured by the vehicle-mounted camera;
• and
• correct the estimation position of the vehicle estimated based on the map data, in response to a recognition of the road section in which the lane quantity increases or decreases, by setting a weighting of the estimation position of the vehicle estimated based on the map data smaller than a case where the road section in which the lane quantity increases or decreases is not recognized.