VEHICLE AND OPERATOR GUIDANCE BY PATTERN RECOGNITION

• US 20160075339A1
• Filed: 04/11/2014
• Published: 03/17/2016
• Est. Priority Date: 04/12/2013
• Status: Active Grant

• Current Assignee: DANA Limited (Caterpillar Incorporated)
• Original Assignee: DANA Limited (Caterpillar Incorporated)
• Inventors: Versteyhe, Mark R.J., Duchene, Thibaut E.
• Granted Patent: US 9,956,966 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60W 2050/0075 Automatic parameter input, automatic initialising or calibrating means
• CPC Class Codes: B60W 2050/0095 Automatic control mode change
• CPC Class Codes: B60W 2556/10 Historical data
• CPC Class Codes: B60W 50/0097 Predicting future conditions
• CPC Class Codes: B60W 50/08 Interaction between the driver and the control system
• CPC Class Codes: B60W 50/14 Means for informing the driver, warning the driver or prompting a driver intervention
• CPC Class Codes: B60Y 2200/15 Fork lift trucks, Industrial trucks
• CPC Class Codes: B66F 9/24 Electrical devices or systems
• CPC Class Codes: G05D 1/0221 involving a learning process
• CPC Class Codes: G09B 19/167 Control of land vehicles

Abstract

A method of vehicle and operator guidance by pattern recognition begins with collecting data on vehicle and operator patterns through sensors. The collected data is combined and analyzed with a pattern recognition algorithm. The combined and analyzed data is compared with patterns in a pattern database. If data matches a pattern in the pattern database, the pattern can be selected. If the data does not match a pattern in the pattern database, a new pattern can be created and selected. Based on the selected pattern, a determination is made to passively assist the operator, selectively assist the operator or passively and actively assist the operator. The determined action is then implemented.

Claims

1. A method of vehicle and operator guidance by pattern recognition, comprising:

receiving data on vehicle and operator patterns through vehicle mounted sensors;

combining and analyzing said collected data with a pattern recognition algorithm;

comparing said combined and analyzed data with patterns in a pattern database;

either accepting the pattern if said combined and analyzed data matches a pattern in said pattern database or marking the combined and analyzed data into a new pattern not in said pattern database and accepting said new pattern;

determining, based on said pattern or new pattern, to passively assist the operator, actively assist the operator or passively and actively assist the operator; and

implementing the determined assistance.

2. The method of claim 1, wherein said vehicle mounted sensors comprise vehicle sensors, sensors for driver actions and fleet management system sensors.

3. The method of claim, 1 wherein said patterns in said pattern database comprise original patterns, updated patterns, received patterns and self-learned patterns.

4. The method of claim 3, wherein self-learned patterns are created by said pattern recognition algorithm by detecting vehicle or operator movements through said vehicle mounted sensors, grouping sensed data into patterns, recording said patterns in said pattern database, and comparing said recorded patterns to determine similarity.

5. The method of claim 4, wherein similar patterns are grouped and saved in the pattern database and nonsimilar patterns are removed from the pattern database.

6. The method of claim 3 wherein said original patterns are preloaded into said pattern database.

7. The method of claim 3, wherein said updated patterns take original patterns and update them based measurements from said vehicle mounted sensors learned during vehicle operation or operator operation.

8. The method of claim 3, wherein said received patterns are not original to the pattern database, but received from other vehicles or a fleet management system by said vehicle mounted sensors.

9. The method of claim 1, wherein an operator overrides the implemented determined assistance.

10. The method of claim 8, wherein said received patterns are created by one or more fleet vehicles performing a repetitive operation and are shared with other fleet vehicles.

11. The method of claim 1, wherein new patterns are entered into said pattern database when said operator records a set of executed repetitive actions.

12. The method of claim 1, wherein passive assistance anticipates the next driver actions based on pattern recognition.

13. The method of clam 1, wherein active assistance initiates the next driver action based on pattern recognition.