Detecting and Mitigating Local Individual Driver Anomalous Behavior

Abstract

Systems and methods for identifying anomalous driving behavior for a vehicle based on past driving behavior are disclosed herein. The method may include receiving a set of time-series driving data for the vehicle, wherein the set of time-series driving data is indicative of a set of operating conditions for the vehicle. Performing machine learning operations on the set of time-series driving data. Identifying a set of anomalous conditions in the time-series driving data based on a result set produced by the machine learning operations, wherein the set of anomalous conditions are indicative of an anomalous vehicle behavior. Comparing the set of anomalous conditions to a set of historical time-series driving data for the vehicle. Generating a vehicle feedback based on the time-series driving data and the comparison of the set of anomalous conditions to the set of historical time-series driving data.

What is claimed: 
     
         1 . A computer implemented method for identifying anomalous driving behavior for a vehicle based on machine learning operations, the method comprising:
 receiving, at one or more processors, a set of time-series driving data, wherein the set of time-series driving data is indicative of a set of operating conditions for the vehicle;   performing, at the one or more processors, machine learning operations on the set the set of time-series driving data;   identifying, at the one or more processors, a set of anomalous conditions in the time-series driving data based on a result set produced by the machine learning operations, wherein the set of anomalous conditions are indicative of an anomalous vehicle behavior; and   modifying, at the one or more processors, the machine learning operations based on the set of time-series driving data and the identified set of anomalous conditions.   
     
     
         2 . The computer implemented method of  claim 1 , wherein the set of time-series driving data is basic safety message data for the vehicle. 
     
     
         3 . The computer implemented method of  claim 2 , wherein the basic safety message data comprise a message id, a conditions dataset, a safety data set, and a status dataset. 
     
     
         4 . The computer implemented method of  claim 1 , wherein the operating conditions comprise time data, coordinate data, movement data, acceleration data, brake system data, and vehicle attribute data. 
     
     
         5 . The computer implemented method of  claim 1 , wherein performing machine learning operations further comprises:
 generating, at the one or more processors, an isolation forest using the time-series driving data.   
     
     
         6 . The computer implemented method of  claim 1 , wherein identifying the set of anomalous conditions in the time-series driving data further comprises:
 identifying, at the one or more processors, unusual frequencies for the time-series driving data.   
     
     
         7 . The computer implemented method of  claim 1 , wherein the anomalous vehicle behavior comprises data indicative of a medical situation, a distracted driver, unidentified road conditions, or combinations thereof. 
     
     
         8 . The computer implemented method of  claim 1 , wherein modifying the machine learning operations based on the set of time-series driving data and the identified set of anomalous conditions further comprises:
 comparing, at the one or more processors, the set of anomalous conditions to a set of threshold values.   
     
     
         9 . A system for identifying anomalous driving behavior for a vehicle based on machine learning operations, the system comprising:
 a network interface configured to interface with a processor;   a plurality of sensors affixed to the vehicle and configured to interface with the processor;   a memory configured to store non-transitory computer executable instructions and configured to interface with the processor; and   the processor configured to interface with the memory, wherein the processor is configured to execute the non-transitory computer executable instructions to cause the processor to:   receive a set of time-series driving data, wherein the set of time-series driving data is indicative of a set of operating conditions for the vehicle;   perform machine learning operations on the set the set of time-series driving data;   identify a set of anomalous conditions in the time-series driving data based on a result set produced by the machine learning operations, wherein the set of anomalous conditions are indicative of an anomalous vehicle behavior; and   modify the machine learning operations based on the set of time-series driving data and the identified set of anomalous conditions.   
     
     
         10 . The system of  claim 9 , wherein the set of time-series driving data is basic safety message data for the vehicle. 
     
     
         11 . The system of  claim 10 , wherein the basic safety message data comprise a message id, a conditions dataset, a safety data set, and a status dataset. 
     
     
         12 . The system of  claim 9 , wherein the operating conditions comprise time data, coordinate data, movement data, acceleration data, brake system data, and vehicle attribute data. 
     
     
         13 . The system of  claim 9 , wherein performing machine learning operations includes generating an isolation forest using the time-series driving data. 
     
     
         14 . The system of  claim 9 , wherein identifying the set of anomalous conditions in the time-series driving data includes identifying unusual frequencies for the time-series driving data. 
     
     
         15 . The system of  claim 9 , wherein the anomalous vehicle behavior includes data indicative of a medical situation, a distracted driver, unidentified road conditions, or combinations thereof. 
     
     
         16 . The system of  claim 9 , wherein modifying the machine learning operations based on the set of time-series driving data and the identified set of anomalous conditions includes comparing the set of anomalous conditions to a set of threshold values. 
     
     
         17 . A non-transitory computer-readable medium storing instructions for identifying anomalous driving behavior for a vehicle based on machine learning operations that, when executed by a processor, cause the processor to:
 receive a set of time-series driving data, wherein the set of time-series driving data is indicative of a set of operating conditions for a vehicle;   perform machine learning operations on the set the set of time-series driving data;   identify a set of anomalous conditions in the time-series driving data based on a result set produced by the machine learning operations, wherein the set of anomalous conditions are indicative of an anomalous vehicle behavior; and   modify the machine learning operations based on the set of time-series driving data and the identified set of anomalous conditions.   
     
     
         18 . The non-transitory computer-readable medium of  claim 17 , wherein the set of time-series driving data is basic safety message data for the vehicle. 
     
     
         19 . The non-transitory computer-readable medium of  claim 18 , wherein the basic safety message data comprise a message id, a conditions dataset, a safety data set, and a status dataset. 
     
     
         20 . The non-transitory computer-readable medium of  claim 17 , wherein the operating conditions comprise time data, coordinate data, movement data, acceleration data, brake system data, and vehicle attribute data.