CALIBRATION FOR AUTONOMOUS VEHICLE OPERATION
First Claim
1. A method comprising:
- receiving data at an autonomous vehicle system comprising a plurality of sensors, the data representing measurements made using the plurality of sensors;
identifying an abnormal sensor measurement based at least in part on the data,wherein a plurality of the measurements, excluding the abnormal sensor measurement, share a common characteristic;
identifying a sensor of the plurality of sensors corresponding to the abnormal sensor measurement;
generating an initial calibration parameter, associated with the sensor, based at least in part on a probabilistic model and the abnormal sensor measurement;
generating an expected sensor measurement, associated with the sensor, based on the data; and
modifying the initial calibration parameter based at least in part on the expected sensor measurement.
2 Assignments
0 Petitions
Accused Products
Abstract
Various embodiments relate generally to autonomous vehicles and associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to provide an autonomous vehicle fleet as a service. In particular, a method may include receiving data associated with a sensor measurement of a perceived object, determining a label associated with the perceived object based on an initial calibration, retrieving log file data associated with the label, determining a calibration parameter associated with the sensor measurement based on the retrieved log file data, and storing the calibration parameter in association with a sensor associated with the sensor measurement. Sensors may be calibrated on the fly while the autonomous vehicle is in operation using one or more other sensors and/or fused data from multiple types of sensors.
252 Citations
20 Claims
-
1. A method comprising:
-
receiving data at an autonomous vehicle system comprising a plurality of sensors, the data representing measurements made using the plurality of sensors; identifying an abnormal sensor measurement based at least in part on the data, wherein a plurality of the measurements, excluding the abnormal sensor measurement, share a common characteristic; identifying a sensor of the plurality of sensors corresponding to the abnormal sensor measurement; generating an initial calibration parameter, associated with the sensor, based at least in part on a probabilistic model and the abnormal sensor measurement; generating an expected sensor measurement, associated with the sensor, based on the data; and modifying the initial calibration parameter based at least in part on the expected sensor measurement. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A method comprising:
-
receiving, at an autonomous vehicle system comprising a plurality of sensors, a plurality of sensor measurements associated with an environmental feature; identifying an abnormal sensor measurement of the plurality of sensor measurements, wherein the abnormal sensor measurement is incongruent with one or more other measurements of the plurality of sensor measurements; identifying a sensor of the plurality of sensors corresponding to the abnormal sensor measurement; determining a plurality of calibration parameters associated with the sensor, wherein at least one parameter of the plurality of calibration parameters is determined based on a statistical computation associated with the environmental feature; determining an expectation model associated with the sensor, wherein the expectation model is configured to output one or more expected sensor measurements; and modifying the plurality of calibration parameters based on an output of the expectation model. - View Dependent Claims (12, 13, 14, 15, 16)
-
-
17. A method comprising:
-
receiving, at an autonomous vehicle system comprising a plurality of sensors, data associated with a measurement made by a sensor of the plurality of sensors, wherein the measurement comprises detection of an object by the sensor; determining a labeled data point associated with the perceived object, wherein the labeled data point is determined based at least in part on an initial calibration of the plurality of sensors; retrieving log file data associated with the labeled data point; determining a calibration parameter associated with the sensor based at least in part on the retrieved log file data; and associating the calibration parameter with information, identifying the sensor, in a memory associated with the autonomous vehicle system. - View Dependent Claims (18, 19, 20)
-
Specification