Information processing apparatus, information processing method, and information processing system
The present disclosure relates to an information processing apparatus, an information processing method, an information processing system, and a program that enable update of an SW to be quickly and safely implemented. The software program (SW) is updated from the vehicle group in which the safety is confirmed, the operation state of the SW after the update is confirmed, and if there is no abnormality, the SW of the vehicle groups other than the vehicle group in which the safety is confirmed is also updated. The present disclosure can be applied to an automated driving technology.
1. An information processing apparatus, comprising:
a central processing unit (CPU) configured to:
update a first software program (SW) to a second SW based on an update SW, wherein the first SW is based on machine learning;
execute an object recognition process based on an image;
compare an object recognition result of the second SW with surrounding information of an object in surroundings, wherein the surrounding information is based on a current position of the object; and
recognize an operation status of the second SW based on the comparison of the object recognition result of the second SW with the surrounding information.
2. The information processing apparatus according to claim 1 , wherein
the second SW corresponds to the first SW relearned by the machine learning.
3. The information processing apparatus according to claim 2 , wherein the CPU is further configured to:
back up the first SW;
update the first SW to the second SW after the back up of the first SW;
compare a first processing result of the second SW with a second processing result of the backed up first SW; and
recognize the operation status of the second SW based on the comparison of the first processing result with the second processing result.
4. The information processing apparatus according to claim 1 , wherein the CPU is further configured to control an operation based on the object recognition result of the first SW.
5. The information processing apparatus according to claim 4 , wherein the CPU is further configured to control the operation based on the object recognition result of the first SW before the update of the first SW.
6. The information processing apparatus according to claim 1 , wherein the CPU is further configured to:
acquire the update SW to update the first SW, wherein the update SW is distributed from a server; and
transmit an operation status recognition result to the server, wherein the operation status recognition result is a result of the recognition of the operation status.
7. The information processing apparatus according to claim 6 , wherein
the server classifies a plurality of information processing apparatuses into groups based on a safety of an operation associated with the first SW,
based on the first SW is not appropriately updated by the update SW, the update SW is sequentially and stepwise distributed to a safest group of the groups,
the safest group comprises a set of information processing apparatuses of the plurality of information processing apparatuses, and
the set of information apparatuses includes the information processing apparatus.
8. The information processing apparatus according to claim 7 , wherein the server distributes the update SW based on a distribution plan at a specific timing.
9. The information processing apparatus according to claim 8 , wherein
the CPU is further configured to estimate the specific timing, at which a specific object is not recognized as the object recognition result of the first SW, as a timing at which control of the operation is unnecessary.
10. The information processing apparatus according to claim 9 , wherein the CPU is further configured to:
control automated driving of a vehicle based on the object recognition result, and
the specific timing corresponds to a timing at which the vehicle travels on a route on which the specific object is not to be recognized as the object recognition result.
11. The information processing apparatus according to claim 7 , wherein the server distributes the update SW based on a distribution plan at a specific timing at which control of the operation is unnecessary.
12. The information processing apparatus according to claim 6 , wherein the server stops the distribution of the update SW to the information processing apparatus based on the operation status recognition result.
13. The information processing apparatus according to claim 12 , wherein the server stops the distribution of the update SW to the information processing apparatus based on a first object recognition accuracy of the second SW is lower than a second object recognition accuracy of the first SW.
14. The information processing apparatus according to claim 6 , wherein
the CPU is further configured to transmit the image and the object recognition result to the server; and
the server relearns the first SW based on the image and the object recognition result and generates the update SW to update the first SW to a relearned state.
15. The information processing apparatus according to claim 14 , wherein
the server distributes the update SW to update the first SW to the relearned state, and
the update SW is distributed based on a specific recognition accuracy of the first SW, and
the specific recognition accuracy is based on the image and the object recognition result.
16. A non-transitory computer-readable medium having stored thereon computer-executable instructions, that when executed by a processor, cause the processor to execute operations, the operations comprising:
updating a first software program (SW) to a second SW based on an update SW, wherein the first SW is based on machine learning;
executing an object recognition process based on an image;
comparing an object recognition result of the second SW with surrounding information of an object in surroundings, wherein the surrounding information is based on a current position of the object; and
recognizing an operation status of the second SW based on the comparison of the object recognition result of the second SW with the surrounding information.
17. The non-transitory computer-readable medium according to claim 16 , the operations further comprising:
acquiring the update SW to update the first SW, wherein the update SW is distributed from a server; and
transmitting an operation status recognition result to the server, wherein the operation status recognition result is a result of the recognition of the operation status.
18. An information processing method, comprising: in an information processing apparatus:
updating a first software program (SW) to a second SW based on an update SW, wherein the first SW is based on machine learning;
executing an object recognition process based on an image;
comparing an object recognition result of the second SW with surrounding information of an object in surroundings, wherein the surrounding information is based on a current position of the object; and
recognizing an operation status of the second SW based on the comparison of the object recognition result of the second SW with the surrounding information.
19. The information processing method according to claim 18 , further comprising:
acquiring the update SW to update the first SW, wherein the update SW is distributed from a server; and
transmitting an operation status recognition result to the server, wherein the operation status recognition result is a result of the recognition of the operation status.
20. An information processing system, comprising:
an information processing apparatus that comprises a central processing unit (CPU) configured to:
update a first software program (SW) to a second SW based on an update SW, wherein the first SW is based on machine learning;
execute an object recognition process based on an image;
compare an object recognition result of the second SW with surrounding information of an object in surroundings, wherein the surrounding information is based on a current position of the object; and
recognize an operation status of the second SW based on the comparison of the object recognition result of the second SW with the surrounding information.
21. The information processing system according to claim 20 , wherein the CPU is further configured to:
acquire the update SW to update the first SW, wherein the update SW is distributed from a server; and
transmitting an operation status recognition result to the server, wherein the operation status recognition result is a result of the recognition of the operation status.