Automated Performance Checks For Autonomous Vehicles

Abstract

Aspects of the disclosure provides for a method for performing checks for a vehicle. In this regard, a plurality of performance checks may be identified including a first check for a detection system of a plurality of detection systems of the vehicle and a second check for map data. A test route for the vehicle may be determined based on a location of the vehicle and the plurality of performance checks. The vehicle may be controlled along the test route in an autonomous driving mode, while sensor data may be received from the plurality of detection systems of the vehicle. An operation mode may be selected based on results of the plurality of performance checks, and the vehicle may be operated in the selected operation mode.

1 . A system in a vehicle, the system comprising:
 memory configured to store map data;   a plurality of sensors configured to detect traffic features and objects in an environment of the vehicle and generate sensor data; and   a computing device including one or more processors configured to perform a plurality of performance checks on the vehicle, the plurality of performance checks including a map check on the map data stored in the memory, the one or more processors being further configured to:
 receive sensor data from at least one of the plurality of sensors, the received sensor data being associated with a stationary object or a traffic feature; 
 determine that the stationary object or the traffic feature is included in the map data stored in the memory; 
 perform the map check by comparing the received sensor data to the map data stored in the memory; 
 select an operation mode from a plurality of operation modes for the vehicle based on a result of the map check; and 
 operate the vehicle in the selected operation mode. 
   
     
     
         2 . The system of  claim 1 , wherein the one or more processors are further configured to:
 detect a difference between the map data and the received sensor data; and   determine whether the difference was due to an error in the map data.   
     
     
         3 . The system of  claim 2 , wherein the one or more processors determine whether the difference was due to an error in the map data by determining which particular sensor of the plurality of sensors generated the sensor data, and then determining whether sensor data collected by a different one of the plurality of sensors should be compared to the map data. 
     
     
         4 . The system of  claim 1 , wherein the one or more processors are further configured to:
 determine whether differences exist in the comparison of the received sensor data to the map data; and   determine that the map check is passed when a threshold number or percentage of traffic features or objects of the map data have locations matching locations of traffic features or objects detected by the plurality of sensors.   
     
     
         5 . The system of  claim 1 , wherein the stationary object is traffic sign. 
     
     
         6 . The system of  claim 1 , wherein the sensor data generated by the plurality of sensors indicates at least one of location or orientation of the stationary object. 
     
     
         7 . The system of  claim 1 , wherein the traffic features and objects include a traffic light. 
     
     
         8 . The system of  claim 1 , wherein the traffic features and objects include a stop sign. 
     
     
         9 . The system of  claim 1 , wherein the traffic features and objects include a crosswalk. 
     
     
         10 . The system of  claim 1 , the one or more processors are configured to:
 select a plurality of road segments based on a location of the vehicle and the plurality of performance checks, wherein each of the plurality of road segments is selected for performing one or more of the plurality of performance checks;   determine a test route for the vehicle by connecting the plurality of road segments and by connecting the location of the vehicle to one of the plurality of road segments; and   control the vehicle along the test route in an autonomous driving mode.   
     
     
         11 . A method for performing a map check for a vehicle, the method comprising:
 storing, by a memory, map data;   detecting, by a plurality of sensors, traffic features and objects in an environment of the vehicle;   generating, by the plurality of sensors, sensor data; and   performing, by one or more processors of a computing device, a map check on the map data stored in the memory by:
 receiving, by the one or more processors, sensor data from at least one of the plurality of sensors, the received sensor data being associated with a stationary object or a traffic feature; 
 determining, by the one or more processors, that the stationary object or the traffic feature is included in the map data stored in the memory; and 
 performing, by the one or more processors, the map check by comparing the received sensor data to the map data stored in the memory, 
 wherein the one or more processors are configured to select an operation mode from a plurality of operation modes for the vehicle based on a result of the map check, and operate the vehicle in the selected operation mode. 
   
     
     
         12 . The method of  claim 11 , further comprising:
 detecting, by the one or more processors, a difference between the map data and the received sensor data; and   determining, by the one or more processors, whether the difference was due to an error in the map data.   
     
     
         13 . The method of  claim 12 , wherein determining whether the difference was due to an error in the map data includes determining which particular sensor of the plurality of sensors generated the sensor data, and then determining whether sensor data collected by a different one of the plurality of sensors should be compared to the map data. 
     
     
         14 . The method of  claim 11 , further comprising:
 determining, by the one or more processors, whether differences exist in the comparison of the received sensor data to the map data; and   determining, by the one or more processors, that the map check is passed when a threshold number or percentage of traffic features or objects of the map data have locations matching locations of traffic features or objects detected by the plurality of sensors.   
     
     
         15 . The method of  claim 11 , wherein the stationary object is traffic sign. 
     
     
         16 . The method of  claim 11 , wherein the sensor data generated by the plurality of sensors indicates at least one of location or orientation of the stationary object. 
     
     
         17 . The method of  claim 11 , wherein the traffic features and objects include a traffic light. 
     
     
         18 . The method of  claim 11 , wherein the traffic features and objects include a stop sign. 
     
     
         19 . The method of  claim 11 , wherein the traffic features and objects include a crosswalk. 
     
     
         20 . The method of  claim 11 , further comprising:
 selecting, by the one or more processors, a plurality of road segments based on a location of the vehicle and a plurality of performance checks, wherein each of the plurality of road segments is selected for performing one or more of the plurality of performance checks;   determining, by the one or more processors, a test route for the vehicle by connecting the plurality of road segments and by connecting the location of the vehicle to one of the plurality of road segments; and   controlling, by the one or more processors, the vehicle along the test route in an autonomous driving mode.