STRIPE: remote driving using limited image data

Research output: Contribution to conferencePaperpeer-review

2 Scopus citations

Abstract

Guiding a remote vehicle when real time image transmission is not possible is an important problem in the field of teleoperation. In such a situation it is impractical for an operator to attempt to directly steer the vehicle using a steering wheel. In semi-autonomous teleoperation, an operator designates the path that the vehicle should follow in an image of the scene transmitted from the vehicle, and the vehicle autonomously follows this path. Previous techniques for semi-autonomous teleoperation require stereo image data, or inaccurately track paths on non-planar terrain. STRIPE (Supervised TeleRobotics using Incremental Polyhedral-Earth geometry) is a new method that I am developing for accurate semi-autonomous teleoperation using monocular image data. This paper provides an summary of the work I am doing for my thesis. This includes the development of the STRIPE robotic system, user studies to empirically measure the accuracy of the STRIPE method under various conditions and with different user interfaces, as well as measurement of baseline data for traditional steering wheel based teleoperation under low-bandwidth and high-latency conditions.

Original languageEnglish (US)
Pages107-108
Number of pages2
StatePublished - Jan 1 1995
Externally publishedYes
EventProceedings of the Conference on Human Factors in Computing Systems. Part 2 (of 2) - Denver, CO, USA
Duration: May 7 1995May 11 1995

Other

OtherProceedings of the Conference on Human Factors in Computing Systems. Part 2 (of 2)
CityDenver, CO, USA
Period5/7/955/11/95

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'STRIPE: remote driving using limited image data'. Together they form a unique fingerprint.

Cite this