Abstract
Robot manipulators require knowledge about their environment in order to perform their desired actions. In several robotic tasks, vision sensors play a critical role by providing the necessary quantity and quality of information regarding the robot's environment. For example, "visual servoing" algorithms may control a robot manipulator in order to track moving objects that are being imaged by a camera. Current visual servoing systems often lack the ability to detect automatically objects that appear within the camera's field of view. In this research, we present a robust "figure/ground" framework for visually detecting objects of interest. An important contribution of this research is a collection of optimization schemes that allow the detection framework to operate within the real-time limits of visual servoing systems. The most significant of these schemes involves the use of "spontaneous" and "continuous" domains. The number and location of continuous domains are allowed to change over time, adjusting to the dynamic conditions of the detection process. We have developed actual servoing systems in order to test the framework's feasibility and to demonstrate its usefulness for visually controlling a robot manipulator.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 101-120 |
| Number of pages | 20 |
| Journal | Robotics and Computer-Integrated Manufacturing |
| Volume | 13 |
| Issue number | 2 |
| DOIs | |
| State | Published - Jun 1997 |
Bibliographical note
Funding Information:1.1. Overview Flexibler obotics ystemsre quires ensoryin formation in order to interacte ffectivelyw ith their environment.T he informationa bouta robot'se nvironment is importanbt ecauseit providest he raw data with which the robot can perceivea, nalyzea nd react to specifico bjectsin the environmenOt.f all the objects that a robot encounterso,n lya subseits significantto the task that the robot has to accomplishW. e term these to be objects of interest, and we concern Acknowledgements--rTehsiesa rchis supportedb y the National ScienceF oundationt hroughC ontracts# IRI-9410003a nd# IRI-9502245th, eC enterf or Transportation Studiest hroughC ontrac#t USDOT/DTRS9 3-G-0017-01, the Departmenotf Energy( SandiaN ationaLl aboratories) throughC ontract#s AC-3752Da nd# AL-3021t,h eArmy High PerformancCeo mputingR esearchC enteru ndert he auspiceso f the Departmenotf the Army, Army Research LaboratorCyo operativAeg reemenNtu mberD AAH04-95-2-0003/ContraNcut mbeDr AAH04-95-C-0008(t hec ontent of which does not necessarilyre flectt he positiono f the policy of the governmenat,n d no official endorsement should be inferred),a nd the McKnight Land-Grant ProfessorshipA ward Program at the University of Minnesota. *Authort o whomc orrespondenscheo uldb e addressed.
Keywords
- Detection
- Frame-differencing
- Real-time robot vision
- Robotic visual servoing
- Sensor-based robot control
- Tracking