Detecting errors in sensor data

1. A system comprising:

one or more processors; and

one or more computer readable storage media communicatively coupled to the one or more processors and storing instructions executable by the one or more processors to:

receive first sensor data;

determine, based at least in part on the first sensor data, a first indication of a first object in the environment;

receive second sensor data;

determine, based at least in part on the first sensor data and the second sensor data, a second indication of a second object in the environment;

determine a difference between the first indication and the second indication; and

at least one of:

initiate a response based at least in part on the difference, or

output, based at least in part on the first sensor data and the second sensor data, an indication to train a machine learning system.

2. The system of claim 1 , wherein the first sensor data is associated with an image sensor and the second sensor data is associated with a light detection and ranging (LIDAR) sensor.

3. The system of claim 2 , wherein:

the image sensor and the LIDAR sensor are disposed on a vehicle; and

the response comprises at least one of:

ignoring a portion of the first sensor data or the second sensor data,

modifying a weight associated with the first sensor data or the second sensor data,

modifying training data used by the machine learning system to train the image sensor or the LIDAR sensor generating a verification request, or

causing the vehicle to change direction.

4. A method comprising:

receiving first sensor data;

determining, based at least in part on the first sensor data, a first indication of a first object in the environment;

receiving second sensor data;

determining, based at least in part on the first sensor data and the second sensor data, a second indication of a second object in the environment;

determining a difference between the first indication and the second indication; and

at least one of:

initiating a response based at least in part on the difference, or

outputting, based at least in part on the first sensor data and the second sensor data, an indication to train a machine learning system.

5. The method of claim 4 , wherein determining the difference between the first indication and the second indication comprises comparing a first object classification associated with the first object to a second object classification associated with the second object to identify a difference between the first object classification and the second object classification.

6. The method of claim 4 , wherein determining the difference between the first indication and the second indication comprises comparing a first parameter of the first object in the environment to a second parameter of the second object in the environment to identify a difference between the first parameter and the second parameter.

7. The method of claim 4 , further comprising:

collecting a plurality of the first sensor data over a period of time;

determining first statistical information based on the plurality of the first sensor data;

comparing the first statistical information with stored statistical information; and

initiating the response based at least in part on the comparing the first statistical information with stored statistical information.

8. The method of claim 4 , wherein:

the first sensor data is associated with a first sensor and the second sensor data is associated with a second sensor,

the first sensor and the second sensor are disposed on a vehicle, and

the response comprises at least one of:

ignoring a portion of the first sensor data,

ignoring a portion of the second sensor data,

modifying a first weight associated with the first sensor data,

modifying a second weight associated with the second sensor data,

modifying training data associated with the first sensor,

modifying training data associated with the second sensor,

generating a verification request, or

causing the vehicle to change direction.

9. The method of claim 4 , wherein at least one of the first sensor data or the second sensor data is associated with at least one of: a location of the first object or the second object, an orientation of the object, an uncertainty, a determination of a presence of the object, or a classification of the object.

10. The method of claim 4 , wherein:

the first sensor data is associated with a first sensor modality, and

the second sensor data is associated a second sensor modality, the second sensor modality different from the first sensor modality.

11. The method of claim 4 , wherein

the first sensor data is detected by a first sensor at a first time, and

the second sensor data is detected by a second sensor at the first time, the method further comprising:

identifying the difference based at least in part on additional data collected, by the first sensor or the second sensor, at a second time later than the first time.

12. The method of claim 4 , wherein determining the difference between the first indication of the first object and the second indication of the second object includes determining that the first object is the same as the second object.

13. The method of claim 4 , wherein:

the first object and the second object comprise a common object;

the first sensor data identifies a first location of the common object;

the second sensor data identifies a second location of the common object; and

the difference comprises a difference between the first location and the second location.

14. The method of claim 13 , further comprising

determining at least one of: a location of an object, an orientation of the object, a number of objects, an uncertainty, a determination of a presence of the object, or a classification of the object associated with the first sensor data based at least in part on a first machine learned model;

determining at least one of: a location of an object, an orientation of the object, a number of objects, an uncertainty, a determination of a presence of the object, or a classification of the object associated with the second sensor data based at least in part on a second machine learned model; and

training the first machine learned model or the second machine learned model using the first sensor data or the second sensor data as ground truth data.

15. The method of claim 14 , wherein:

the first sensor data is associated with a first confidence level,

the second sensor data is associated with a second confidence level, and

the response comprises modifying at least one of the first confidence level or the second confidence level.

16. A computer-readable, storage medium having computer-executable instructions stored thereupon which, when executed by a computer, cause the computer to:

receive first sensor data;

determine, based at least in part on the first sensor data, a first indication of a first object in the environment;

receive second sensor data;

determine, based at least in part on the first sensor data and the second sensor data, a second indication of a second object in the environment;

determine a difference between the first indication and the second indication; and

at least one of:

initiate a response based at least in part on the difference, or

output, based at least in part on the first sensor data and the second sensor data, an indication to train a machine learning system.

17. The computer-readable storage medium of claim 16 , wherein:

the first sensor data is associated with a first sensor modality, and

the second sensor data is associated a second sensor modality, the second sensor modality different from the first sensor modality.

18. The computer-readable storage medium of claim 16 , wherein determining the difference between the first indication and the second indication comprises comparing a first object classification associated with the first object to a second object classification associated with the second object to identify a difference between the first object classification and the second object classification.

19. The computer-readable storage medium of claim 16 , wherein at least one of the first sensor data or the second sensor data is associated with at least one of: a location of an object, an orientation of the object, a number of objects, an uncertainty, a determination of a presence of the object, or a classification of the object.

20. The computer-readable storage medium of claim 16 , wherein:

the first sensor data is associated with a first sensor and the second sensor data is associated with a second sensor,

the first sensor and the second sensor are disposed on a vehicle, and

the response comprises at least one of:

ignoring a portion of the first sensor data,

ignoring a portion of the second sensor data,

modifying a first weight associated with the first sensor data,

modifying a second weight associated with the second sensor data,

modifying training data associated with the first sensor,

modifying training data associated with the second sensor,

generating a verification request, or

causing the vehicle to change direction.