RK : A Real-Time Kernel for a Distributed System With Predictable Response
Insup Lee, Robert B. King, Richard P. Paul
- Year
- 1988
- Citations
- 4
- Access
- Open access
Abstract
Robotics applications must execute in real-time. In addition, complex robotics applications include many physically distributed components such as manipulator arms and sensors. This paper presents the real-time kernel RK which is designed to facilitate the development of a distributed sensory system with multiple arms and sensors. The goal of the kernel is to support distributed applications that require predictable timing behavior. Our kernel design guarantees predictable response times by scheduling processes and communications based on timing constraints. In addition, the kernel provides a set of primitives that can be used to implement applications requiring predictable timing behavior. These primitives allow the specification of timing requirements that can be guaranteed in advance by the scheduler and the direct control of devices by application processes for faster and predictable feedback control. To illustrate the use of our kernel, this paper also describes a multiple sensory system which is being ported to our distributed test-bed.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002