Name
Title | ||
|---|---|---|
An extendable framework for expectation-based visual servoing using environment models |
Abstract | ||
|---|---|---|
Visual servoing is a manipulation control strategy that precisely positions objects using imprecisely calibrated camera-lens-manipulator systems. In order to quickly and easily integrate sensor-based manipulation strategies such as visual servoing into robotic systems, a system frame- work and a task representation must exist which facilitates this integration. The framework must also be extendable so that obsolete sensor systems can be easily replaced or extended as new technologies become available. In this paper, we present a framework for expectation-based visual servoing which visually guides tasks based on the expected visual appearance of the task. The appearance of the task is generated by a model of the environment that uses texture-mapped geometric models to represent objects. A system structure which facilitates the integra- tion of various configurations of visual servoing systems is presented, as well as a hardware implementation of the proposed system and experimental results using a stereo camera system. quickly and easily integrated. This framework must be able to take advantage of the benefits visual servoing provides, specifically the ability to control manipulator motion using high bandwidth visual feedback, while avoiding the pitfall of being dependent on a particular visual sensor hardware configuration. The proper framework will allow the integra- tion of any of a number of visual sensor hardware configu- rations, such as monocular camera systems, stereo pairs with varying baselines and verging angles, multi-baseline stereo systems, and laser rangefinders. The framework should also facilitate the integration of visual servoing with other sensor-based manipulation strategies. In its basic form, image-based visual servoing is a purely reactive manipulator motion strategy. The objective of the control system is simply to make some set of measured fea- ture states defined in the camera's sensor space match some set of desired states defined in the same space by moving the manipulator. In order for the execution of a robotic task to benefit from the advantages visual servoing provides, a representation of the task based on some model of the envi- ronment must exist. This representation must be capable of |
Year | DOI | Venue |
|---|---|---|
1995 | 10.1109/ROBOT.1995.525283 | Robotics and Automation, 1995. Proceedings., 1995 IEEE International Conference |
Keywords | Field | DocType |
manipulators,position control,robot vision,environment models,expectation-based visual servoing,extendable framework,imprecisely calibrated camera-lens-manipulator systems,manipulation control strategy,robotic systems,sensor systems replacement,sensor-based manipulation strategy integration,stereo camera system,texture-mapped geometric models | Robotic systems,System framework,Stereo camera,Computer vision,System structure,Computer science,Robustness (computer science),Control engineering,Visual servoing,Solid modeling,Artificial intelligence,Visual appearance | Conference |
Volume | ISSN | ISBN |
1 | 1050-4729 | 0-7803-1965-6 |
Citations | PageRank | References |
5 | 0.66 | 16 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Bradley J. Nelson | 1 | 1263 | 202.74 |
| Khosla, P.K. | 2 | 931 | 123.84 |