System and method for detecting a condition prompting an update to an autonomous vehicle driving model

Abstract

Systems and methods for implementing one or more autonomous features for autonomous and semi-autonomous control of one or more vehicles are provided. More specifically, image data may be obtained from an image acquisition device and processed utilizing one or more machine learning models to identify, track, and extract one or more features of the image utilized in decision making processes for providing steering angle and/or acceleration/deceleration input to one or more vehicle controllers. In some instances, techniques may be employed such that the autonomous and semi-autonomous control of a vehicle may change between vehicle follow and lane follow modes. In some instances, at least a portion of the machine learning model may be updated based on one or more conditions.

What is claimed is: 
     
         1 . A method comprising:
 receiving a first autonomous vehicle model;   detecting a condition associated with a performance of the first autonomous vehicle model;   determining that the first autonomous vehicle model should be updated based on the detected condition;   receiving at least one update for the first autonomous vehicle model;   applying the at least one update; and   generating a second autonomous vehicle model based on the at least one update.   
     
     
         2 . The method of  claim 1 , wherein detecting a condition associated with the performance of the first autonomous vehicle model includes determining that at least one of a quantity of course corrections or a quantity of course deviations exceeded a threshold within a period of time. 
     
     
         3 . The method of  claim 2 , wherein a course correction includes determining that an input associated with a manual override was received. 
     
     
         4 . The method of  claim 3 , wherein the input associated with the manual override includes one of a manual velocity change or manual steering angle change. 
     
     
         5 . The method of  claim 2 , wherein a course deviation includes determining that a path traveled by an autonomous vehicle is different from a projected path traveled by the autonomous vehicle. 
     
     
         6 . The method of  claim 2 , wherein the threshold varies based on one or more of time, location, date, or weather condition. 
     
     
         7 . The method of  claim 1 , wherein the at least one update includes one or more model parameters for a portion of the first autonomous vehicle model. 
     
     
         8 . The method of  claim 1 , further comprising:
 recording a location associated with one or more course corrections and/or course deviations.   
     
     
         9 . The method of  claim 1 , wherein the second autonomous vehicle model is received at an autonomous vehicle. 
     
     
         10 . The method of  claim 1 , wherein the second autonomous vehicle model is generated at an autonomous vehicle. 
     
     
         11 . A system comprising:
 a memory;   a processor in communication with the memory, wherein the processor executes instructions stored in the memory, which cause the processor to execute a method, the method comprising:   receiving a first autonomous vehicle model;   detecting a condition associated with a performance of the first autonomous vehicle model;   determining that the first autonomous vehicle model should be updated based on the detected condition;   receiving at least one update for the first autonomous vehicle model;   applying the at least one update; and   generating a second autonomous vehicle model based on the at least one update.   
     
     
         12 . The system of  claim 11 , wherein detecting a condition associated with the performance of the first autonomous vehicle model includes determining that at least one of a quantity of course corrections or a quantity of course deviations exceeded a threshold within a period of time. 
     
     
         13 . The system of  claim 12 , wherein a course correction includes determining that an input associated with a manual override was received. 
     
     
         14 . The system of  claim 13 , wherein the input associated with the manual override includes one of a manual velocity change or manual steering angle change. 
     
     
         15 . The system of  claim 12 , wherein a course deviation includes determining that a path traveled by an autonomous vehicle is different from a projected path traveled by the autonomous vehicle. 
     
     
         16 . A non-transitory computer readable medium having stored thereon instructions, which when executed by a processor cause the processor to execute a method, the method comprising:
 receiving a first autonomous vehicle model;   detecting a condition associated with a performance of the first autonomous vehicle model;   determining that the first autonomous vehicle model should be updated based on the detected condition;   receiving at least one update for the first autonomous vehicle model;   applying the at least one update; and   generating a second autonomous vehicle model based on the at least one update.   
     
     
         17 . The non-transitory computer readable medium of  claim 16 , wherein detecting a condition associated with the performance of the first autonomous vehicle model includes determining that at least one of a quantity of course corrections or a quantity of course deviations exceeded a threshold within a period of time. 
     
     
         18 . The non-transitory computer readable medium of  claim 17 , wherein a course correction includes determining that an input associated with a manual override was received. 
     
     
         19 . The non-transitory computer readable medium of  claim 18 , wherein the input associated with the manual override includes one of a manual velocity change or manual steering angle change. 
     
     
         20 . The non-transitory computer readable medium of  claim 16 , wherein a course deviation includes determining that a path traveled by an autonomous vehicle is different from a projected path traveled by the autonomous vehicle.