LEARNING AND REASONING TO ENHANCE ENERGY EFFICIENCY IN TRANSPORTATION SYSTEMS

• US 20080249667A1
• Filed: 04/10/2007
• Published: 10/09/2008
• Est. Priority Date: 04/09/2007
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Horvitz, Eric J., Krumm, John C.
• Application Number:
  US11/733,701
• Publication Number:
  US 20080249667A1
• Time in Patent Office: Days
• US Class Current: 701/1
• CPC Class Codes: B60W 40/072 Curvature of the road
• CPC Class Codes: B60W 40/076 Slope angle of the road
• CPC Class Codes: B60W 40/12 related to parameters of the vehicle itself , e.g. tyre models
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

There is employment of machine learning, reasoning, and optimization included in a multi-attribute utility framework to learn and control energy systems to enhance the efficiency of vehicles. This can include energy systems included in vehicles that employ multiple energy sources. There is construction of models that provide inferences given historical information and/or real-time sensing of contextual information that are used in optimization. Such inferences about such key uncertainties as that route being taken are used in optimizing the expected utilities.

Claims