Information processing system, information processing method, and information processing apparatus
Provided are an information processing system, an information processing method, and an information processing apparatus that are capable of diagnosing sensor degradation. A recognition result of a predetermined recognition target based on results of sensing performed by a plurality of sensors mounted in a vehicle is acquired, the acquired recognition result is compared with another recognition result different from the acquired recognition result so that a comparison result is output, and performance degradation of each sensor is evaluated on the basis of the comparison result.
1 . An information processing system, comprising:
a processor configured to:
acquire a plurality of first recognition results of a recognition target, based on sensing operations by a plurality of sensors in a first vehicle,
wherein each of the plurality of first recognition results includes at least one of a position or an object name of the recognition target;
calculate a confidence value of each of the plurality of first recognition results based on the at least one of the position or the object name of the recognition target;
acquire a confidence value of a second recognition result, wherein the second recognition result is different from the plurality of first recognition results;
compare the calculated confidence value of a specific recognition result of the plurality of first recognition results with the acquired confidence value of the second recognition result, to output a comparison result;
detect a change point of the confidence value of the specific recognition result based on the comparison result that is larger than a first threshold, wherein
the change point corresponds to a point of fluctuation of the calculated confidence value of the specific recognition result;
compare a change of the calculated confidence value of the specific recognition result at the change point with a second threshold;
evaluate performance degradation of each sensor of the plurality of sensors, based on the comparison between the change of the calculated confidence value at the change point and the second threshold; and
control a self-driving operation of the first vehicle based on the evaluated performance degradation of each sensor of the plurality of sensors.
2 . The information processing system according to claim 1 , wherein the second recognition result is a past recognition result of the first vehicle.
3 . The information processing system according to claim 2 , further comprising a memory configured to accumulate the acquired confidence value of the second recognition result,
wherein the processor is further configured to compare the confidence value of each of the plurality of first recognition results with the accumulated confidence value of the second recognition result.
4 . The information processing system according to claim 1 , wherein the second recognition result is a recognition result of a second vehicle different from the first vehicle.
5 . The information processing system according to claim 4 , wherein
the second recognition result is based on a result of a sensing operation by a sensor of the second vehicle, and
the sensor of the second vehicle is same as a sensor of the plurality of sensors in the first vehicle.
6 . The information processing system according to claim 4 , wherein
the second recognition result is based on a result of a sensing operation by a sensor of the second vehicle, and
an operating time of the sensor of the second vehicle and an operating time of a sensor of the plurality of sensors in the first vehicle are same.
7 . The information processing system according to claim 4 , further comprising a cloud server and a memory in the cloud server, wherein
the memory is configured to accumulate the acquired confidence value of the second recognition result, and
the processor is further configured to compare the calculated confidence value of each of the plurality of first recognition results with the accumulated confidence value of the second recognition result.
8 . The information processing system according to claim 1 , wherein the processor is further configured to suspend the self-driving operation of the first vehicle based on the evaluated performance degradation of a sensor of the plurality of sensors is lower than a third threshold.
9 . The information processing system according to claim 8 , wherein the processor is further configured to determine an insurance premium associated with the first vehicle based on the evaluated performance degradation of the sensor is lower than the third threshold.
10 . The information processing system according to claim 9 , wherein the processor is further configured to:
notify, based on the evaluated performance degradation of the sensor is lower than the third threshold, a user or an owner of the first vehicle of information to request an approval of an update of an insurance contract with the insurance premium; and
control, based on the approval of the update of the insurance contract with the insurance premium, the first vehicle to continue the self-driving operation.
11 . The information processing system according to claim 9 , wherein the processor is further configured to:
notify, based on the evaluated performance degradation of the sensor is lower than the third threshold, a user or an owner of the first vehicle of information to request an approval of an update of an insurance contract with the insurance premium; and
suspend, based on the update of the insurance contract with the insurance premium is not approved, the self-driving operation of the first vehicle.
12 . The information processing system according to claim 1 , further comprising a cloud server, wherein the processor is in the cloud server.
13 . The information processing system according to claim 1 , wherein
the plurality of sensors performs the sensing operations in a state in which the first vehicle is in a space, and
in the space, the first vehicle is at a specific distance from the recognition target.
14 . The information processing system according to claim 13 , wherein
the space is not affected by a plurality of environmental factors,
the plurality of environmental factors include wind and light, and
the space corresponds to an indoor space.
15 . The information processing system according to claim 13 , wherein
the space is affected by a plurality of environmental factors,
the plurality of environmental factors includes wind and light, and
the processor is further configured to evaluate the performance degradation of each sensor of the plurality of sensors based on the plurality of environmental factors.
16 . An information processing method, comprising:
acquiring a plurality of first recognition results of a recognition target, based on sensing operations by a plurality of sensors in a vehicle, wherein
each of the plurality of first recognition results includes at least one of a position or an object name of the recognition target;
calculating a confidence value of each of the plurality of first recognition results based on the at least one of the position or the object name of the recognition target;
acquiring a confidence value of a second recognition result, wherein the second recognition result is different from the plurality of first recognition results;
comparing the calculated confidence value of a specific recognition result of the plurality of first recognition results with the acquired confidence value of the second recognition result, for outputting a comparison result;
detecting a change point of the confidence value of the specific recognition result based on the comparison result that is larger than a first threshold, wherein
the change point corresponds to a point of fluctuation of the calculated confidence value of the specific recognition result;
comparing a change of the calculated confidence value of the specific recognition result at the change point with a second threshold;
evaluating performance degradation of each sensor of the plurality of sensors, based on the comparison between the change of the calculated confidence value at the change point and the second threshold; and
controlling a self-driving operation of the vehicle based on the evaluated performance degradation of each sensor of the plurality of sensors.
17 . An information processing apparatus, comprising:
a processor configured to:
acquire a plurality of first recognition results of a recognition target, based on sensing operations by a plurality of sensors in a vehicle, wherein
each of the plurality of first recognition results includes at least one of a position or an object name of the recognition target;
calculate a confidence value of each of the plurality of first recognition results based on the at least one of the position or the object name of the recognition target;
acquire a confidence value of a second recognition result, wherein the second recognition result is different from the plurality of first recognition results;
compare the calculated confidence value of a specific recognition result of the plurality of first recognition results with the acquired confidence value of the second recognition result, to output a comparison result;
detect a change point of the confidence value of the specific recognition result based on the comparison result that is larger than a first threshold, wherein
the change point corresponds to a point of fluctuation of the calculated confidence value of the specific recognition result;
compare a change of the calculated confidence value of the specific recognition result at the change point with a second threshold;
evaluate performance degradation of each sensor of the plurality of sensors, based on the comparison between the change of the calculated confidence value at the change point and the second threshold; and
control a self-driving operation of the vehicle based on the evaluated performance degradation of each sensor of the plurality of sensors.