S
Sebastian Thrun
Researcher at Stanford University
Publications - 437
Citations - 108035
Sebastian Thrun is an academic researcher from Stanford University. The author has contributed to research in topics: Mobile robot & Robot. The author has an hindex of 146, co-authored 434 publications receiving 98124 citations. Previous affiliations of Sebastian Thrun include University of Pittsburgh & ETH Zurich.
Papers
More filters
Proceedings ArticleDOI
Active Sensing for High-Speed Offroad Driving
TL;DR: An active control strategy for scanning laser sensors on autonomous vehicles traveling offroad at high speeds is proposed and results comparing the active sensing method to a passive sensing method are compared.
Proceedings ArticleDOI
Deformable Image Mosaicing for Optical Biopsy
TL;DR: A new method that integrates deformable surface models into the image mosaicing algorithms to efficiently deal with accumulated image registration errors and introduce a local alignment algorithm to accommodate local scene deformations is presented.
A System for Three-Dimensional Robotic Mapping of Underground Mines
Michael Montemerlo,Dirk Haehnel,David I. Ferguson,Rudolph Triebel,Wolfram Burgard,Scott M. Thayer,William Whittaker,Sebastian Thrun +7 more
TL;DR: Two robotic systems for acquiring high-resolution volumetric maps of underground mines are described, one of which has been deployed in an operational coal mine in Bruceton, Pennsylvania, and the other has been used to generate interactive 3-dimensional maps.
Posted Content
Learning Hierarchical Object Maps Of Non-Stationary Environments with mobile robots
TL;DR: In this article, an algorithm for learning object models of non-stationary objects found in office-type environments is presented. But it does so through a two-level hierarchical representation, which links individual objects with generic shape templates of object classes.
Book
Explanation-based learning for mobile-robot perception
TL;DR: First experiments applying explanation-based neural network learning to the problem of learning object recognition for a mobile robot show that EBNN is able to use approximate prior knowledge to significantly reduce the number of training examples required to learn to recognize distant doors.