Information processing apparatus, information processing method, and mobile object

1. An information processing apparatus, comprising:

at least one sensor configured to acquire peripheral information regarding a periphery of a first mobile object; and

at least one processor configured to:

calculate first posture information regarding a posture of the first mobile object;

acquire, from an apparatus different from the first mobile object, attribute information regarding an attribute of a second mobile object that is in the periphery of the first mobile object, wherein the attribute information includes second posture information regarding a posture of the second mobile object;

generate label information based on the first posture information and the second posture information; and

generate learning data based on the acquired peripheral information and the acquired attribute information, wherein

the learning data includes association of the acquired peripheral information and the generated label information, and

the learning data is generated for extraction of an attribute of a target mobile object.

2. The information processing apparatus according to claim 1 , wherein the attribute information includes information associated with at least one of a location, a vehicle type, or a model of the second mobile object.

3. The information processing apparatus according to claim 1 , wherein the apparatus different from the first mobile object is the second mobile object.

4. The information processing apparatus according to claim 1 , wherein the at least one sensor is further configured to detect at least one of image information or depth information of the periphery of the first mobile object, as the peripheral information.

5. The information processing apparatus according to claim 1 , the at least one processor is further configured to:

detect the second mobile object in the periphery of the first mobile object; and

acquire the attribute information of the second mobile object based on the detection of the second mobile object.

6. The information processing apparatus according to claim 1 , wherein the at least one processor is further configured to calculate the first posture information based on the peripheral information.

7. The information processing apparatus according to claim 1 , wherein the at least one processor is further configured to calculate, as the label information, a relative posture of the second mobile object relative to the first mobile object based on the first posture information and the second posture information.

8. The information processing apparatus according to claim 7 , wherein

the peripheral information includes information of a reference object that is a reference for the calculation of the relative posture,

the first posture information is information of the posture of the first mobile object relative to the reference object, and

the second posture information is information of the posture of the second mobile object relative to the reference object.

9. The information processing apparatus according to claim 8 , wherein

the first posture information is information of the posture of the first mobile object relative to a reference direction associated with the reference object, and

the second posture information is information of the posture of the second mobile object relative to the reference direction.

10. The information processing apparatus according to claim 8 , wherein the at least one processor is further configured to:

acquire, when a distance between a detection position of a detection of the peripheral information is detected and the reference object is larger than a threshold value, reference peripheral information, wherein the reference peripheral information is detected at a proximity position closer to the reference object than the detection position; and

calculate the relative posture at the detection position based on a basis of the reference peripheral information.

11. The information processing apparatus according to claim 10 , wherein the at least one processor is further configured to:

calculate reference posture information regarding the posture of the first mobile object relative to the reference object at the proximity position based on the reference peripheral information; and

calculate a posture change of the first mobile object during movement from the detection position to the proximity position.

12. The information processing apparatus according to claim 11 , wherein the at least one processor is further configured to calculate the first posture information regarding the posture of the first mobile object relative to the reference object at the detection position based on a basis of the reference posture information and the posture change.

13. The information processing apparatus according to claim 2 , wherein the at least one processor is further configured to acquire information regarding a timing of generation of the attribute information.

14. The information processing apparatus according to claim 1 , wherein the at least one processor is further configured to control a timing of detection of the peripheral information based on a timing of generation of the attribute information.

15. The information processing apparatus according to claim 14 , wherein

the apparatus different from the first mobile object continuously generates the attribute information, and

the at least one processor is further configured to control detection of the peripheral information such that the peripheral information is continuously detected during a period of the continuous generation of the attribute information.

16. An information processing method to be executed by a computer system, the information processing method comprising:

acquiring peripheral information regarding a periphery of a first mobile object;

calculating first posture information regarding a posture of the first mobile object;

acquiring, from an apparatus different from the first mobile object, attribute information regarding an attribute of a second mobile object that is in the periphery of the first mobile object, wherein the attribute information includes second posture information regarding a posture of the second mobile object;

generating label information based on the first posture information and the second posture information; and

generating learning data based on the acquired peripheral information and the acquired attribute information, wherein

the learning data includes association of the acquired peripheral information and the generated label information, and

the learning data is generated for extraction of an attribute of a target mobile object.

17. A non-transitory computer-readable medium having stored thereon computer-executable instructions, which when executed by a computer, cause the computer to execute operations, the operations comprising:

acquiring peripheral information regarding a periphery of a first mobile object;

calculating first posture information regarding a posture of the first mobile object;

acquiring, from an apparatus different from the first mobile object, attribute information regarding an attribute of a second mobile object that is in the periphery of the first mobile object, wherein the attribute information includes second posture information regarding a posture of the second mobile object;

generating label information based on the first posture information and the second posture information; and

generating learning data based on the acquired peripheral information and the acquired attribute information, wherein

the learning data includes association of the acquired peripheral information and the generated label information, and

the learning data is generated for extraction of an attribute of a target mobile object.

18. A mobile object, comprising:

at least one sensor configured to acquire peripheral information regarding a periphery of the mobile object; and

at least one processor configured to:

calculate first posture information regarding a posture of the mobile object;

acquire, from a different apparatus, attribute information regarding an attribute of a peripheral mobile object that is in the periphery of the mobile object, wherein the attribute information includes second posture information regarding a posture of the peripheral mobile object;

generate label information based on the first posture information and the second posture information; and

generate learning data based on the acquired peripheral information and the acquired attribute information, wherein

the learning data includes association of the acquired peripheral information and the generated label information, and

the learning data is generated for extraction of an attribute of a target mobile object.