Training of vehicles to improve autonomous capabilities

• US 10,528,836 B1
• Filed: 09/22/2019
• Issued: 01/07/2020
• Est. Priority Date: 11/20/2017
• Status: Active Grant

• Current Assignee: Ashok Krishnan
• Original Assignee: Ashok Krishnan
• Inventors: Krishnan, Ashok
• Primary Examiner(s): Rahmjoo, Manuchehr
• Application Number:
  US16/578,345
• Publication Number:
  US 20200019801A1
• Time in Patent Office: 107 Days
• CPC Class Codes: A61B 3/113 for determining or recording eye movement
• CPC Class Codes: A61B 5/225 of the fingers, e.g. by monitoring hand-grip force
• CPC Class Codes: A61B 5/6893 Cars
• CPC Class Codes: B60W 40/09 Driving style or behaviour
• 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: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 20/46 Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
• CPC Class Codes: G06V 20/59 inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
• CPC Class Codes: G06V 20/597 Recognising the driver's state or behaviour, e.g. attention or drowsiness
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris
• CPC Class Codes: G06V 40/70 Multimodal biometrics, e.g. combining information from different biometric modalities

Abstract

Systems and methods to improve performance, reliability and learning to enhance autonomy of vehicles. Sensors capture human eye movements, hearing, hand grip and contact area on steering wheel, the positions of accelerator and brake pedals from the wall behind them as well as from the foot. Outside event signatures corresponding to human reactions and actions are then extracted form these sensors and correlated to events, status and situations acquired using vehicle and outside environment sensors. These outside event signatures are then used to train vehicles to improve their autonomous capabilities.

Claims

1. A method comprising:

recording a signature of an event outside a vehicle driven by a human, the vehicle having a brake pedal and an accelerator pedal controlled by a foot of the human, and a wall behind these pedals, the signature comprising data relating to;

(i) eye movement of the human, and (ii) distance of the accelerator and brake pedals from the wall behind the pedals as well as from the foot of the human, wherein the signature is used to train vehicles to become partially or fully autonomous or to improve their autonomous functioning.

2. The method of claim 1, wherein the signature further comprises data relating to the grip and contact area of a hand of the human on a steering wheel.

3. The method of claim 1, wherein the signature further comprises aural sensor data.

4. The method of claim 1, wherein the signature further comprises one or more of the following data related to the vehicle:

geolocation, timestamp, speed.