Operating a vehicle in response to detecting a faulty sensor using calibration parameters of the sensor

Abstract

In an embodiment, a processor is configured to perform, while a vehicle is driving in an uncontrolled environment, a self-calibration routine for each sensor from the plurality of sensors to determine at least one calibration parameter value associated with that sensor. The processor is further configured to determine, while the vehicle is driving in the uncontrolled environment, and automatically in response to performing the self-calibration routine, that at least one sensor from the plurality of sensors has moved and/or is inoperative based on the at least one calibration parameter value associated with the at least one sensor being outside a predetermined acceptable range. The processor is further configured to perform, in response to determining that at least one sensor from the plurality of sensors has moved and/or is inoperative, at least one remedial action at the vehicle while the vehicle is driving in the uncontrolled environment.

1 . A computer-implemented method comprising:
 monitoring, by a computing system, a plurality of calibration parameter values associated with a plurality of sensors on a plurality of vehicles based on a plurality of self-calibration routines performed on the plurality of vehicles;   determining, by the computing system, that a sensor of the plurality of sensors has moved or is inoperative based on a calibration parameter value of the plurality of calibration parameter values is outside a predetermined acceptable range; and   causing, by the computing system, a remedial action to be performed based on the determining that the sensor of the plurality of sensors has moved or is inoperative.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising:
 determining, by the computing system, sensors of a sensor type on a threshold number of vehicles of the plurality of vehicles have moved or are inoperative; and   causing, by the computing system, the sensors of the sensor type to be investigated or replaced.   
     
     
         3 . The computer-implemented method of  claim 1 , further comprising:
 determining, by the computing system, a threshold number of vehicles of the plurality of vehicles have sensors that have moved or are inoperative; and   causing, by the computing system, at least one of: driving patterns, driver behavior, and environmental conditions associated with the threshold number of vehicles to be analyzed.   
     
     
         4 . The computer-implemented method of  claim 1 , further comprising:
 determining, by the computing system, the predetermined acceptable range based on a machine learning model;   updating, by the computing system, the predetermined acceptable range based on the plurality of calibration parameter values and the machine learning model; and   providing, by the computing system, the updated predetermined acceptable range to the plurality of vehicles.   
     
     
         5 . The computer-implemented method of  claim 1 , wherein the remedial action includes changing a driving mode of a vehicle of the plurality of vehicles associated with the sensor that has moved or is inoperative to at least one of: a fully autonomous mode, a partially autonomous mode, a manual mode, an eco mode, a sports mode, a four wheel drive mode, and a two wheel drive mode. 
     
     
         6 . The computer-implemented method of  claim 1 , wherein the remedial action includes at least one of: causing sensor data collected by the sensor that has moved or is inoperative to be ignored or modified and causing an alert to be sent by a vehicle of the plurality of vehicles associated with the sensor that has moved or is inoperative. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein the sensor is a camera and the calibration parameter value is associated with at least one of: a focal length, an optical center, a scale factor, a principal point, a skew, a distortion, a rolling shutter time, and a geometric distortion associated with the camera. 
     
     
         8 . The computer-implemented method of  claim 1 , wherein the sensor is an inertial measurement unit and the calibration parameter value is associated with at least one of: an accelerometer bias, a gyroscope bias, a thermal response, a sensitivity, a sample rate, a linearity, and a noise level associated with the inertial measurement unit. 
     
     
         9 . The computer-implemented method of  claim 1 , wherein the sensor is a radar and the calibration parameter value is associated with at least one of: an operating frequency, a wavelength, a beamwidth, a pulse width, an antenna radiation pattern, a peak output power, and a pulse repetition frequency associated with the radar. 
     
     
         10 . The computer-implemented method of  claim 1 , wherein the sensor is a lidar and the calibration parameter value is associated with at least one of: a beam intensity, a point density, a field-of-view, a scan pattern, a timestamp offset, and a beam angular offset associated with the lidar. 
     
     
         11 . A system comprising:
 at least one processor; and   a memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:
 monitoring a plurality of calibration parameter values associated with a plurality of sensors on a plurality of vehicles based on a plurality of self-calibration routines performed on the plurality of vehicles; 
 determining that a sensor of the plurality of sensors has moved or is inoperative based on a calibration parameter value of the plurality of calibration parameter values is outside a predetermined acceptable range; and 
 causing a remedial action to be performed based on the determining that the sensor of the plurality of sensors has moved or is inoperative. 
   
     
     
         12 . The system of  claim 11 , the operations further comprising:
 determining sensors of a sensor type on a threshold number of vehicles of the plurality of vehicles have moved or are inoperative; and   causing the sensors of the sensor type to be investigated or replaced.   
     
     
         13 . The system of  claim 11 , the operations further comprising:
 determining a threshold number of vehicles of the plurality of vehicles have sensors that have moved or are inoperative; and   causing at least one of: driving patterns, driver behavior, and environmental conditions associated with the threshold number of vehicles to be analyzed.   
     
     
         14 . The system of  claim 11 , the operations further comprising:
 determining the predetermined acceptable range based on a machine learning model;   updating the predetermined acceptable range based on the plurality of calibration parameter values and the machine learning model; and   providing the updated predetermined acceptable range to the plurality of vehicles.   
     
     
         15 . The system of  claim 11 , wherein the remedial action includes changing a driving mode of a vehicle of the plurality of vehicles associated with the sensor that has moved or is inoperative to at least one of: a fully autonomous mode, a partially autonomous mode, a manual mode, an eco mode, a sports mode, a four wheel drive mode, and a two wheel drive mode. 
     
     
         16 . A non-transitory computer-readable storage medium including instructions that, when executed by at least on processor of a computing system, cause the computing system to perform operations comprising:
 monitoring a plurality of calibration parameter values associated with a plurality of sensors on a plurality of vehicles based on a plurality of self-calibration routines performed on the plurality of vehicles;   determining that a sensor of the plurality of sensors has moved or is inoperative based on a calibration parameter value of the plurality of calibration parameter values is outside a predetermined acceptable range; and   causing a remedial action to be performed based on the determining that the sensor of the plurality of sensors has moved or is inoperative.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 16 , the operations further comprising:
 determining sensors of a sensor type on a threshold number of vehicles of the plurality of vehicles have moved or are inoperative; and   causing the sensors of the sensor type to be investigated or replaced.   
     
     
         18 . The non-transitory computer-readable storage medium of  claim 16 , the operations further comprising:
 determining a threshold number of vehicles of the plurality of vehicles have sensors that have moved or are inoperative; and   causing at least one of: driving patterns, driver behavior, and environmental conditions associated with the threshold number of vehicles to be analyzed.   
     
     
         19 . The non-transitory computer-readable storage medium of  claim 16 , the operations further comprising:
 determining the predetermined acceptable range based on a machine learning model;   updating the predetermined acceptable range based on the plurality of calibration parameter values and the machine learning model; and   providing the updated predetermined acceptable range to the plurality of vehicles.   
     
     
         20 . The non-transitory computer-readable storage medium of  claim 16 , wherein the remedial action includes changing a driving mode of a vehicle of the plurality of vehicles associated with the sensor that has moved or is inoperative to at least one of: a fully autonomous mode, a partially autonomous mode, a manual mode, an eco mode, a sports mode, a four wheel drive mode, and a two wheel drive mode.