SELECTIVE PERCEPTION FOR ROBOT DRIVING

In this thesis, the author describes how reasoning can be integrated with perception, how task knowledge can be used to select perceptual targets, and how this selection dramatically reduces the computational cost of perception. These concepts are illustrated for the domain of driving by a robot driving program called Ulysses. A microscopic traffic simulator called PHAROS is developed to define the street environment for this research.

• Supplemental Notes:
  • Publication Date: 1992 Published By: University Microfilms International, Ann Arbor, Mich. Remarks: Thesis (Ph. D.)--Carnegie Mellon University, 1992
• Corporate Authors:

  Carnegie Mellon University

  Wean Hall 4323
  5000 Forbes Avenue
  Pittsburgh, PA  United States  15213-3890
• Authors:
  • Reece, Douglas A
• Publication Date: 1992

Language

• English

Media Info

• Pagination: iii, 199 p.

Subject/Index Terms

• TRT Terms: Automobile driving; Robotics; Simulation

Filing Info

• Accession Number: 00773348
• Record Type: Publication
• Source Agency: UC Berkeley Transportation Library
• Files: PATH
• Created Date: Nov 17 1999 12:00AM