Robot localization using variance sampling
A method of localizing a robot includes receiving odometry information plotting locations of the robot and sensor data of the environment about the robot. The method also includes obtaining a series of odometry information members, each including a respective odometry measurement at a respective time. The method also includes obtaining a series of sensor data members, each including a respective sensor measurement at the respective time. The method also includes, for each sensor data member of the series of sensor data members, (i) determining a localization of the robot at the respective time based on the respective sensor data, and (ii) determining an offset of the localization relative to the odometry measurement at the respective time. The method also includes determining whether a variance of the offsets determined for the localizations exceeds a threshold variance. When the variance among the offsets exceeds the threshold variance, a signal is generated.
1. A method of robot localization, the method comprising:
receiving, at data processing hardware of a robot, odometry information indicating a position of the robot within an environment at each of a plurality of times;
receiving, at the data processing hardware, sensor data of the environment from at least one sensor of the robot, the sensor data indicating a localization of the robot for each of the plurality of times;
determining, by the data processing hardware, an offset of the localization of the robot relative to the odometry information for each of the plurality of times, and a variance of the offset;
adjusting, by the data processing hardware, relative weights of the odometry information and the sensor data based on comparing the variance of the offset to a threshold variance; and
controlling, by the data processing hardware, movement of the robot.
2. The method of claim 1 , further comprising:
determining, by the data processing hardware, a current location of the robot using the adjusted relative weights of the odometry information and the sensor data; and
further controlling, by the data processing hardware, movement of the robot based on the current location.
3. The method of claim 1 further comprising, when the variance of the offset exceeds the threshold variance, reducing, by the data processing hardware, a weight of the sensor data relative a weight of the odometry information.
4. The method of claim 3 further comprising, when the variance of the offset exceeds the threshold variance, generating an unreliable sensor data signal.
5. The method of claim 4 wherein the unreliable sensor data signal comprises a notification to an operator of the robot.
6. The method of claim 1 , further comprising, when the variance of the offset does not exceed the threshold variance, increasing, by the data processing hardware, a weight of the odometry information relative to a weight of the sensor data.
7. The method of claim 1 , wherein the sensor data comprises a reference sensor data member and a plurality of comparison sensor data members.
8. The method of claim 7 , further comprising determining, by the data processing hardware, the localization of the robot based on a pairwise analysis of the reference sensor data member to each of the plurality of comparison sensor data members.
9. The method of claim 1 , wherein the at least one sensor of the robot comprises a three-dimensional volumetric image sensor, and the sensor data comprises a three-dimensional volumetric point cloud.
10. The method of claim 1 , wherein the variance is a sample variance.
11. The method of claim 1 further comprising:
receiving, by the data processing hardware, the odometry information and the sensor data during the movement.
12. A robot comprising:
a body;
at least one sensor;
data processing hardware; and
memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
receiving odometry information indicating a position of the robot within an environment at each of a plurality of times;
receiving sensor data of the environment from the at least one sensor, the sensor data indicating a localization of the robot for each of the plurality of times;
determining an offset of the localization of the robot relative to the odometry information for each of the plurality of times, and a variance of the offset; and
adjusting relative weights of the odometry information and the sensor data based on comparing the variance of the offset to a threshold variance.
13. The robot of claim 12 , wherein the operations further comprise:
determining a current location of the robot using the adjusted relative weights of the odometry information and the sensor data; and
controlling movement of the robot based on the current location.
14. The robot of claim 12 , wherein the operations further comprise reducing a weight of the sensor data relative a weight of the odometry information.
15. The robot of claim 14 , wherein the operations further comprise generating an unreliable sensor data signal when the variance of the offset exceeds the threshold variance.
16. The robot of claim 12 , wherein the operations further comprise increasing a weight of the odometry information relative to a weight of the sensor data when the variance of the offset does not exceed the threshold variance.
17. The robot of claim 12 , wherein the sensor data comprises a reference sensor data member and a plurality of comparison sensor data members.
18. The robot of claim 17 , wherein the operations further comprise determining the localization of the robot based on a pairwise analysis of the reference sensor data member to each of the plurality of comparison sensor data members.
19. The robot of claim 12 , wherein the at least one sensor of the robot comprises a three-dimensional volumetric image sensor, and the sensor data comprises a three-dimensional volumetric point cloud.
20. The robot of claim 12 , wherein the variance is a sample variance.