User data-based autonomous vehicle system

• US 10,606,276 B2
• Filed: 09/29/2017
• Issued: 03/31/2020
• Est. Priority Date: 09/30/2016
• Status: Active Grant

• Current Assignee: Faraday & Future Inc.
• Original Assignee: Faraday & Future Inc.
• Inventors: Fischer, Evan Roger
• Primary Examiner(s): Shaawat, Mussa A
• Application Number:
  US15/721,085
• Publication Number:
  US 20190049981A1
• Time in Patent Office: 914 Days
• CPC Class Codes: B60W 2050/0088 Adaptive recalibration
• CPC Class Codes: B60W 50/08 Interaction between the driver and the control system
• CPC Class Codes: B60W 50/10 Interpretation of driver requests or demands
• CPC Class Codes: G05D 1/0011 associated with a remote control arrangement
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0221 involving a learning process
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

Examples of the disclosure are directed to using vehicle users'"'"' subjective evaluation of autonomous vehicle performance to adjust operation of one or more autonomous vehicle systems, such as an adaptive cruise control system. In some examples, a vehicle can perform an autonomous maneuver, and can use automotive sensors to collect data describing one or more quantitative aspects of that vehicle during the maneuver, such as make, model, GPS coordinates, mileage, speed, engine activity, or LIDAR data, among other possibilities. In some examples, a control system can receive subjective feedback inputted by the vehicle'"'"'s user that indicates one or more qualitative evaluations of the completed autonomous maneuver. In some examples, a control system may perform statistical analysis of collected vehicle data and of subjective feedback input by vehicle users to identify correlations between quantitative vehicle parameters, specified types of user feedback and/or autonomous vehicle maneuvers.

Claims

1. A system comprising:

one or more sensors configured to sense one or more parameters of a vehicle;

one or more processors operatively coupled to the one or more sensors; and

a memory including instructions, which when executed by the one or more processors, cause the one or more processors to perform a method comprising;

causing the vehicle to perform an autonomous vehicle maneuver in accordance with a determination by an autonomous vehicle system;

detecting, via the one or more sensors, objective data of the one or more parameters of the vehicle associated with the autonomous vehicle maneuver;

receiving subjective data input by one or more users of the vehicle corresponding to an evaluation of the autonomous vehicle maneuver by the one or more users of the vehicle;

determining whether to adjust a configuration of the autonomous vehicle system based on the objective data and the subjective data; and

determining a sensitivity of a vehicle user to one or more autonomous vehicle maneuvers by comparing subjective data received from the vehicle user with subjective data received from several other vehicle users.

2. The system of claim 1, wherein additional objective data is detected and additional subjective data is received each time a vehicle performs an autonomous vehicle maneuver.

3. The system of claim 1, wherein detecting objective data comprises determining one or more of:

a vehicle type, a number of vehicle occupants, a vehicle mileage, camera data, radar data, LIDAR data, GPS data, temperature data, weather data, brake activity, accelerator activity, a steering angle, a torque input, driver monitoring info, vehicle diagnostics data, steering angle and column torque sensor data, a vehicle speed, and inertial measurement data.

4. The system of claim 1, wherein subjective data includes data input by a user that includes the user'"'"'s qualitative evaluation of an autonomous vehicle maneuver according to one or more of validity, severity, vehicle controllability, and user exposure.

5. The system of claim 1, wherein an autonomous vehicle maneuver comprises one or more of:

autonomous lane keeping, autonomous blind spot monitoring, adaptive cruise control, evasive steer-assist, and predictive collision mitigation systems.

6. The system of claim 1, wherein the method further comprises modifying one or more parameters of the autonomous vehicle system to perform the one or more autonomous vehicle maneuvers according to the determined sensitivity of the vehicle user.

7. The system of claim 1, wherein the method further comprises:

determining a modification of one or more parameter s of the autonomous vehicle system, based on a correlation of the detected objective data and the received subjective data indicating the modification of the one or more parameters, to improve the autonomous vehicle system'"'"'s performance of one or more autonomous driving maneuvers.

8. The system of claim 7, wherein modifying one or more parameters of the autonomous vehicle system comprises changing one or more of a warning threshold, an activation speed, a condition for feature suppression, a duration from performing an autonomous maneuver, a control algorithm, vehicle firmware, vehicle software, or vehicle sensor settings.

9. The system of claim 1, wherein subjective data is received from the vehicle user from one or more of a microphone, a touchscreen, navigation buttons, a keyboard, or a mobile computing device.

10. The system of claim 1, wherein the method further comprises:

predicting one or more failures of the one or more autonomous vehicle systems based on the detected objective data and the received subjective data.

11. A vehicle comprising:

one or more sensors configured to sense one or more parameters of a vehicle;

one or more processors operatively coupled to the one or more sensors; and

a memory including instructions, which when executed by the one or more processors, cause the one or more processors to perform a method comprising;

causing the vehicle to perform an autonomous vehicle maneuver in accordance with a determination by an autonomous vehicle system;

detecting, via the one or more sensors, objective data of the one or more parameters of the vehicle associated with the autonomous vehicle maneuver;

receiving subjective data input by one or more users of the vehicle corresponding to an evaluation of the autonomous vehicle maneuver by the one or more users of the vehicle;

determining whether to adjust a configuration of the autonomous vehicle system based on the objective data and the subjective data; and

determining a sensitivity of a vehicle user to one or more autonomous vehicle maneuvers by comparing subjective data received form the vehicle user with subjective data received from several other vehicle users.