An Architecture for Sensor Fusion in a Mobile Robot
Abstract
This paper describes sensor fusion in the context of an autonomous mobile robot, the NAVLAB system, based on a commercial truck with computer controls and studded with cameras and other sensors. This paper describes the software architecture of the NAVLAB, consisting of two parts; a 'whiteboard' system called CODGER that is similar to a blackboard but supports parallelism in the knowledge source modules, and an organized collection of perceptual and navigational modules tied together by the CODGER database/communication system. The NAVLAB vehicle is a commercial truck modified by adding sensors, electronic controls, and on-board computers and power generators. It will be completely self-contained, requiring neither a cable tethering it to an off-board mainframe computer, nor an electronic telecommunications tether. Telecommunications gear is present for data recording and tele-operation, but is not required for computer control of the vehicle. The control systems of the vehicle include computer control of a hydraulic drive/braking system computer control of the steering wheel, and processors to monitor and control engine functions. A global system clock and a processor maintain a primitive vehicle position estimate based on dead reckoning. An inertial navigation system is also on-board. Keywords; CODGER (Communications Database with Geometric Reasoning).
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1986
- Accession Number
- ADA168075
Entities
People
- Anthony Stentz
- Charles E. Thorpe
- Steven Arthur Shafer
Organizations
- Carnegie Mellon University