Online lidar intensity normalization

1. A vehicle computing system configured to control a vehicle, the vehicle computing system comprising:

one or more processors; and

a non-transitory computer-readable medium storing instructions that, when executed by the one or more processors, cause the vehicle computing system to perform operations comprising:

accumulating point data output by a first channel from among a plurality of channels of a light detection and ranging (Lidar) unit while the vehicle is in operation, the point data comprising a plurality of raw intensity values that correspond to a particular surface type;

calculating a median intensity value based on the plurality of raw intensity values;

generating an intensity normalization multiplier for the first channel based on the median intensity value, wherein application of the intensity normalization multiplier to the median intensity value results in a reflectivity value that corresponds to the particular surface type;

applying the intensity normalization multiplier to subsequent point data output by the first channel, wherein application of the intensity normalization multiplier to the subsequent point data results in a plurality of normalized intensity values;

determining a motion plan for the vehicle based on the plurality of normalized intensity values; and

controlling one or more operations of the vehicle based on the motion plan.

2. The vehicle computing system of claim 1 , wherein the operations further comprise:

accumulating additional point data output by a second channel from among the plurality of channels of the Lidar unit;

generating an additional intensity normalization multiplier for the second channel; and

applying the additional intensity normalization multiplier to the additional point data produced by the second channel.

3. The vehicle computing system of claim 1 , wherein the operations further comprise:

updating the intensity normalization multiplier based on the subsequent point data output by the first channel; and

applying the updated intensity normalization multiplier to further point data output by the first channel.

4. The vehicle computing system of claim 3 , wherein the updating of the intensity normalization multiplier is performed after a predefined time interval.

5. The vehicle computing system of claim 1 , further comprising determining the reflectivity value that corresponds to the particular surface type based on reference map data.

6. The vehicle computing system of claim 1 , wherein:

the point data further comprises a set of data points;

each data point from the set of data points corresponds to the particular surface type; and

each raw intensity value of the plurality of raw intensity values corresponds to a data point from the set of data points.

7. The vehicle computing system of claim 6 , wherein the accumulating of the point data output by the first channel comprises:

obtaining a plurality of data points output by the first channel over a predefined time interval; and

identifying the set of data points from the plurality of data points based on an association with one or more historic data points known to correspond to the particular surface type.

8. The vehicle computing system of claim 1 , wherein the applying of the intensity normalization multiplier to the subsequent point data output by the first channel comprises applying the multiplier to one or more raw intensity values included in the subsequent point data.

9. The vehicle computing system of claim 1 , wherein generating the intensity normalization multiplier for the first channel comprises dividing the reflectivity value by the median intensity value.

10. A method comprising:

accumulating point data output by a first channel from among a plurality of channels of a light detection and ranging (Lidar), the point data comprising a plurality of raw intensity values that correspond to a particular surface type;

calculating a median intensity value based on the plurality of raw intensity values;

generating, by one or more processors of a vehicle computing system, an intensity normalization multiplier for the first channel based on the median intensity value, wherein application of the intensity normalization multiplier to the median intensity value results in a reflectivity value that corresponds to the particular surface type;

applying, by the one or more processors of the vehicle computing system, the intensity normalization multiplier to the point data output by the first channel, wherein application of the intensity normalization multiplier to the point data results in a plurality of normalized intensity values;

determining, by the one or more processors of the vehicle computing system, a motion plan for a vehicle based on the plurality of normalized intensity values; and

controlling one or more operations of the vehicle based on the motion plan.

11. The method of claim 10 , further comprising:

accumulating additional point data output by a second channel from among the plurality of channels of the Lidar unit;

generating an additional intensity normalization multiplier for the second channel; and

applying the additional intensity normalization multiplier to the additional point data produced by the second channel.

12. The method of claim 10 , further comprising:

updating the intensity normalization multiplier based on subsequent point data output by the first channel; and

applying the updated intensity normalization multiplier to further point data output by the first channel.

13. The method of claim 12 , wherein the updating of the intensity normalization is performed periodically at a predefined time interval.

14. The method of claim 10 , wherein:

the point data further comprises a set of data points;

each data point from the set of data points corresponds to the particular surface type; and

each raw intensity value of the plurality of raw intensity values corresponds to a data point from the set of data points.

15. The method of claim 10 , wherein the accumulating of the point data output by the first channel comprises:

obtaining a plurality of data points output by the first channel over a predefined time interval; and

identifying a subset of the plurality of data points that correspond to the particular surface type based on reference map data that includes one or more historic data points known to correspond to the particular surface type.

16. The method of claim 10 , wherein the applying of the intensity normalization multiplier to the subsequent point data output by the first channel comprises applying the multiplier to one or more raw intensity values included in the subsequent point data.

17. The method of claim 10 , further comprising determining the reflectivity value that corresponds to the particular surface type based on reference map data.

18. The method of claim 10 , wherein generating the intensity normalization multiplier for the first channel comprises dividing the reflectivity value by the median intensity value.

19. A non-transitory computer-readable medium storing a set of instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

accumulating point data output by a first channel from among a plurality of channels of a light detection and ranging (Lidar) unit of an autonomous vehicle system, the point data comprising a plurality of raw intensity values that correspond to a particular surface type;

calculating a median intensity value based on the plurality of raw intensity values;

generating an intensity normalization multiplier for the first channel based on the median intensity value, wherein application of the intensity normalization multiplier to the median intensity value results in a reflectivity value that corresponds to the particular surface type;

applying the intensity normalization multiplier to the point data output by the first channel, wherein application of the intensity normalization multiplier to the point data results in a plurality of normalized intensity values;

determining a motion plan for a vehicle based on the plurality of normalized intensity values; and

controlling one or more operations of the vehicle based on the motion plan.

20. The non-transitory computer-readable medium of claim 19 , wherein the operations further comprise:

periodically updating, at predefined time intervals, the intensity normalization multiplier based on subsequent point data output by the first channel during each predefined time interval; and

applying the updated intensity normalization multiplier to further point data output by the first channel.