Accident fault determination for autonomous vehicles

Patent metadata

Field	Value
Publication number	US-9972054-B1
Application number	US-201514951798-A
Country	US
Kind code	B1
Filing date	Nov 25, 2015
Priority date	May 20, 2014
Publication date	May 15, 2018
Grant date	May 15, 2018

Abstract

Methods and systems for determining fault for an accident involving a vehicle having one or more autonomous and/or semi-autonomous operation features are provided. According to certain aspects, performance data indicative of the performance of the features may be used to determine fault for a vehicle accident, such as a collision, by allocating fault for the accident between a vehicle operator, the autonomous operation features, or a third party. The allocation of fault may be used to determine an adjustment to an insurance policy and/or adjust coverage levels for an insurance policy. The allocation of fault may further be used to adjust risk levels or profiles associated with the autonomous or semi-autonomous operation features, which may be applied to other vehicles having the same or similar features.

First claim

What is claimed is:

1. A computer system for determining fault for a vehicle crash, the system comprising one or more processors or transceivers of a server configured to:
receive, at the server via a communication network, an indication of the vehicle crash involving a vehicle having one or more autonomous vehicle technologies, the indication being transmitted from an on-board computer or mobile device via wireless communication or data transmission;
receive, at the server via the communication network, a vehicle data log including (a) vehicle-mounted sensor data generated by one or more sensors of the vehicle, and (b) autonomous feature data regarding use, configuration, or settings of one or more autonomous features before and during the vehicle crash, the autonomous feature data including a plurality of control signals generated by the one or more autonomous vehicle technologies to control the vehicle, and the (a) vehicle-mounted sensor data, and (b) autonomous feature data being transmitted from the on-board computer or mobile device via wireless communication or data transmission;
analyze, by the server, entries in the vehicle data log regarding the (a) vehicle-mounted sensor data, and (b) autonomous feature data regarding the use, configuration, or settings of the one or more autonomous features before and during the vehicle crash to determine an operating control status of the vehicle at the time of the vehicle crash;
determine, by the server, whether or not the vehicle crash was an unavoidable accident that was the fault of a third party based upon the determined operating control status, wherein the third party includes a pedestrian, an operator of another vehicle, or another autonomous vehicle; and
when the vehicle was operating in an autonomous mode before and during the vehicle crash, and the vehicle crash was not the fault of any third party:
evaluate, by the server, the plurality of control signals indicated by the entries of the vehicle data log to identify control actions attempted by the one or more autonomous vehicle technologies;
determine, by the server and based upon the identified control actions, fault contributions of each of the following as a cause of the vehicle crash: (i) the one or more autonomous features failed to generate control signals to control the vehicle to avoid the vehicle crash and (ii) one or more hardware components of the vehicle failed to implement the control signals generated by the one or more autonomous features;
determine and assign, by the server, a percentage of fault for the vehicle crash to the one or more autonomous features that were in control of the vehicle at the time of the vehicle crash based upon the determined fault contributions;
perform, by the server, one or more of the following actions based upon the assigned percentage of fault: adjust an insurance policy associated with the vehicle, determine a coverage level associated with the insurance policy, present the determination to a reviewer to verify the assigned percentage of fault, or present the determination to a customer for review of the assigned percentage of fault; and
cause, by communication from the server to a user computing device, an indication of the one or more actions performed to be presented to a user associated with the user computing device via a display of the user computing device.

2. The computer system of claim 1 , wherein the percentage of fault for the vehicle crash is assigned to the one or more autonomous features only after the one or more processors determine that the one or more autonomous features attempted to return control of the vehicle to a vehicle operator prior to the vehicle crash, but failed to provide sufficient time to transfer control.

3. The computer system of claim 1 , wherein determining the percentage of fault for the vehicle crash that is assigned to the one or more autonomous features involves the one or more processors determining a point of impact on the vehicle.

4. The computer system of claim 1 , wherein determining the percentage of fault for the vehicle crash that is assigned to the one or more autonomous features involves the one or more processors determining, based upon control signals or outputs from the autonomous operation features before and during the vehicle crash, whether the one or more autonomous features were ineffective in controlling the vehicle.

5. The computer system of claim 1 , wherein determining the percentage of fault for the vehicle crash that is assigned to the one or more autonomous features involves the one or more processors determining the vehicle crash resulted from physical defects in physical components of the one or more autonomous features.

6. The computer system of claim 1 , wherein determining the percentage of fault for the vehicle crash that is assigned to the one or more autonomous features involves the one or more processors determining that the one or more autonomous features had a chance to avoid the vehicle crash, but no action was taken.

7. The computer system of claim 1 , wherein determining the percentage of fault for the vehicle crash that is assigned to the one or more autonomous features involves the one or more processors determining environmental conditions of the vehicle before and during the vehicle crash, and using the one or more autonomous features' test or known performance in such environmental conditions.

8. The computer system of claim 1 , wherein determining whether the third party was at fault includes determining a point of impact for one or more vehicles, a speed of the vehicle, and an indication of a traffic signal.

9. A computer-implemented method of determining fault for a vehicle crash, the method comprising:
receiving, at one or more processors or transceivers of a server via a communication network an indication of the vehicle crash involving a vehicle having one or more autonomous vehicle technologies, the indication being transmitted from an on-board computer or mobile device via wireless communication or data transmission;
receiving, at the one or more processors or transceivers of the server via the communication network, a vehicle data log including (a) vehicle-mounted sensor data generated by one or more sensors of the vehicle and (b) autonomous feature data regarding use, configuration, or settings of one or more autonomous features before and during the vehicle crash, at the one or more processors or transceivers, the autonomous feature data including a plurality of control signals generated by the one or more autonomous vehicle technologies to control the vehicle, and the (a) vehicle-mounted sensor data, and (b) autonomous feature data being transmitted from the on-board computer or mobile device via wireless communication or data transmission;
analyzing, by the one or more processors of the server, entries in the vehicle data log regarding the (a) vehicle-mounted sensor data, and (b) autonomous feature data regarding the use, configuration, or settings of the one or more autonomous features before and during the vehicle crash, at the one or more processors, to determine an operating control status of the vehicle at the time of the vehicle crash;
determining, by the one or more processors of the server whether or not the vehicle crash was an unavoidable accident that was the fault of a third party based upon the determined operating control status, wherein the third party includes a pedestrian, an operator of another vehicle, or another autonomous vehicle; and
when the vehicle was operating in an autonomous mode before and during the vehicle crash, and the vehicle crash was not the fault of any third party:
evaluating, by the one or more processors of the server the plurality of control signals

Assignees

• State Farm Mutual Automobile Insurance Co

Inventors

• Konrardy Blake
• Christensen Scott T
• Hayward Gregory
• Farris Scott

Classifications

• G07C5/08

  Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time · CPC title

• G05D1/0088

  characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours (using knowledge based models G06N5/00) · CPC title

• G06Q40/08 Primary

  Insurance · CPC title

• G07C5/085

  using electronic data carriers · CPC title

• G06Q40/00

  Finance; Insurance; Tax strategies; Processing of corporate or income taxes · CPC title