Self-position estimation apparatus, self-position estimation method, and program
A self-position estimation apparatus comprises a camera part; an environmental data storage part that stores information that changes according to the position of a mobile object on a travel route in association with the position information thereof; a first estimation part that estimates the position of mobile object from sensor data containing information that changes according to the position of mobile object and the information in the environmental data storage part; a second estimation part that estimates the self-position of mobile object from a known object included in an image inputted from the camera part; a weighting determination part that determines weighting to the position estimation results by the first estimation part and the second estimation part; and a self-position calculation part that calculates a self-position by linearly combining the self-positions estimated by the first estimation part and the second estimation part using the result from the weighting determination part.
1. A self-position estimation apparatus comprising:
a camera part; and
at least a processor; and
a memory in circuit communication with the processor,
wherein the processor is configured to execute program instructions stored in the memory to implement:
an environmental data storage part that stores information that changes according to a position of a mobile object on a travel route in association with position information thereof;
a first estimation part that estimates the position of the mobile object from sensor data containing information that changes according to the position of the mobile object and the information in the environmental data storage part;
a second estimation part that estimates the position of the mobile object on the basis of a known object image included in an image inputted from the camera part;
a weighting determination part that determines weightings for the position of the mobile object estimated by the first estimation part and the second estimation part;
a self-position calculation part that calculates the position of the mobile object by linearly combining the positions estimated by the first estimation part and the second estimation part using the weightings determined by the weighting determination part;
a continuity determination part that determines whether or not the position of the mobile object calculated by the self-position calculation part is continuous; and
a marking part that marks the information held by the environmental data storage part with a predetermined marking on the basis of the result by the continuity determination part.
2. The self-position estimation apparatus according to claim 1 , wherein
the weighting determination part calculates a weight w for the position estimated by the first estimation part on the basis of a similarity between the information in the environmental data storage part and the sensor data and sets a weight for the position estimated by the second estimation part to (1−w).
3. The self-position estimation apparatus according to claim 1 , wherein
the weighting determination part changes the weightings to reduce the weighting for the position estimated by the first estimation part relating to the marked information,
the self-position calculation part recalculates the position using the changed weightings, and
the marking part rewrites the position information of the information associated with the marked information to the recalculated position.
4. The self-position estimation apparatus according to claim 1 , wherein
the marked information is excluded from targets of the linear combining by the self-position calculation part when it is determined that there is no continuity at the position a calculated using the marked information.
5. The self-position estimation apparatus according to claim 1 , wherein at least one type of data out of data obtained by using LiDAR, data obtained from a depth sensor, and SfM-MVS data is as the information that changes according to the position of the mobile object on the travel route.
6. A self-position estimation method performed by a self-position estimation apparatus comprising:
a camera part;
an environmental data storage part that stores information that changes according to a position of a mobile object on a travel route in association with position information thereof;
a first estimation part that estimates the position of the mobile object from sensor data containing information that changes according to the position of the mobile object and the information in the environmental data storage part; and
a second estimation part that estimates the position of the mobile object on the basis of a known object image included in an image inputted from the camera part,
wherein the self-position estimation method comprises:
determining weightings for the position of the mobile object estimated by the first estimation part and the second estimation part;
calculating the position of the mobile object by linearly combining the positions estimated by the first estimation part and the second estimation part using the weightings;
determining whether or not the calculated position of the mobile object is continuous; and
marking the information held by the environmental data storage part with a predetermined marking on the basis of the result of determining whether or not the calculated self-position is continuous.
7. The self-position estimation method according to claim 6 , wherein calculating the weightings comprises calculating a weight w for the position estimated by the first estimation part on the basis of a similarity between the information in the environmental data storage part and the sensor data, and setting a weight for the position estimated by the second estimation part to (1−w).
8. The self-position estimation method according to claim 6 , further comprising:
changing the weightings to reduce the weighting for the position estimated by the first estimation part relating to the marked information;
recalculating the position using the changed weightings; and
rewriting the position information of the information associated with the marked information to the recalculated position.
9. The self-position estimation method according to claim 6 , further comprising:
excluding the marked information from targets of the linear combining by the self-position calculation part when it is determined that there is no continuity at the position calculated using the marked information.
10. The self-position estimation method according to claim 6 , wherein at least one type of data out of data obtained by using LiDAR, data obtained from a depth sensor, and SfM-MVS data is used as the information that changes according to the position of the mobile object on the travel route.
11. A non-transitory computer-readable recording medium storing a program executable by a computer comprising:
a camera part;
an environmental data storage part that stores information that changes according to a position of a mobile object on a travel route in association with position information thereof;
a first estimation part that estimates the position of the mobile object from sensor data containing information that changes according to the position of the mobile object and the information in the environmental data storage part; and
a second estimation part that estimates the position of the mobile object on the basis of a known object image included in an image inputted from the camera part,
wherein the program is executable by the computer to perform processing comprising:
determining weightings for the position of the mobile object estimated by the first estimation part and the second estimation part;
calculating the position of the mobile object by linearly combining the positions estimated by the first estimation part and the second estimation part using the weightings;
determining whether or not the calculated position of the mobile object is continuous; and
marking the information held by the environmental data storage part with a predetermined marking on the basis of the result of determining whether or not the calculated self-position is continuous.
12. The non-transitory computer-readable recording medium according to claim 11 , wherein
calculating the weightings comprises calculating a weight w for the position estimated by the first estimation part on the basis of a similarity between the information in the environmental data storage part and the sensor data, and
setting for the position estimated by the second estimation part to (1−w).
13. The non-transitory computer-readable recording medium according to claim 11 , wherein the processing further comprises:
changing the weightings to reduce the weighting for the position estimated by the first estimation part relating to the marked information;
recalculating the position using the changed weightings; and
rewriting the position information of the information associated with the marked information to the recalculated position.
14. The non-transitory computer-readable recording medium according to claim 11 , wherein the processing further comprises:
excluding the marked information from targets of the linear combining by the self-position calculation part when it is determined that there is no continuity at the position calculated using the marked information.
15. The non-transitory computer-readable recording medium according to claim 11 , wherein at least one type of data out of data obtained by using LiDAR, data obtained from a depth sensor, and SfM-MVS data is used as the information that changes according to the position of the mobile object on the travel route.