Abstract
Four projects within a managed program of research, the automation of subsea tasks, are outlined which together are concerned with implementing a distributed knowledge-based system (KBS) for sensor interpretation. The four projects are concerned with specifying and implementing a distributed KBS architecture on an array of transputer processors, design of a knowledge base which encapsulates a subset of an experienced sonar operator's expertise, design of image processing and feature measurement techniques for segmenting and characterizing candidate objects and shadows in a sonar scan, and sensor fusion using data derived simultaneously from an ultrasound and a video camera. The combined objective of the projects is to investigate tools and techniques for both algorithmic and knowledge-based processing applied to sector scan sonar, ultrasound, and video images, in order to build both local and global descriptions of the environment surrounding an autonomous robotic system. Prospects for future extensions are considered.
Original language | English |
---|---|
Title of host publication | Proceedings of the Sixth International Symposium on Unmanned Untethered Submersible Technology |
Subtitle of host publication | y; Ellicott City, MD, USA; ; 12 June 1989 through 14 June 1989 |
Pages | 401-416 |
Number of pages | 16 |
Publication status | Published - 1989 |
Event | Proceedings of the Sixth International Symposium on Unmanned Untethered Submersible Technology Technology - Ellicott City, MD, USA Duration: 12 Jun 1989 → 14 Jun 1989 |
Conference
Conference | Proceedings of the Sixth International Symposium on Unmanned Untethered Submersible Technology Technology |
---|---|
City | Ellicott City, MD, USA |
Period | 12/06/89 → 14/06/89 |