Distributed knowledge base program for vehicular localization and work-site management

• US 8,224,500 B2
• Filed: 09/11/2008
• Issued: 07/17/2012
• Est. Priority Date: 09/11/2008
• Status: Active Grant

• Current Assignee: Deere & Company
• Original Assignee: Deere & Company
• Inventors: Anderson, Noel Wayne
• Primary Examiner(s): Nguyen, Kim T
• Application Number:
  US12/208,721
• Publication Number:
  US 20100063648A1
• Time in Patent Office: 1,405 Days
• Field of Search: 701 23- 25, 701/27, 701/35, 701 40- 41, 701 59- 60, 701/1, 706/45, 706/50
• US Class Current: 701/1
• 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: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/043 Distributed expert systems; Blackboards

Abstract

The illustrative embodiments provide a computer program product for controlling a vehicle. In an illustrative embodiment, a computer program product is comprised of a computer recordable media having computer usable program code for identifying a dynamic condition. When the dynamic condition is identified, computer usable program code using a knowledge base controls the vehicle.

Claims

1. A computer program product comprising:

a non-transitory computer recordable media;

computer usable program code, stored on the computer recordable media, for identifying a dynamic condition, and responsive to identifying the dynamic condition, controlling the vehicle using a knowledge base comprising an a priori knowledge base, an online knowledge base, and a learned knowledge base, wherein the online knowledge base dynamically provides information to a machine controller of the vehicle which enables adjustment to sensor data processing by the machine controller, and wherein the machine controller identifies an environment around the vehicle using the online knowledge base.

2. The computer program product of claim 1, further comprising:

computer usable program code for selectively updating the learned knowledge base using the dynamic conditions.

3. The computer program product of claim 2, wherein the selectively updating step comprises:

computer usable program code for updating the learned knowledge base with changes to a set of objects in the environment.