Dynamic Visual Servo Control of Robots: An Adaptive Image-Based Approach.
Abstract
The objective of this dissertation is to develop analytical tools for the design and evaluation of feedback compensators for dynamic vision-based robot control. Sensory systems, such as computer vision, can be used to measure relative robot end-effector (or tool) positions to derive feedback signals for control of end-effector positioning. The role of vision as the feedback transducer affects closed-loop dynamics, and a visual feedback compensator is required. Vision-based robot control research has focused on vision processing issues (e.g., image filtering, structured lighting environments, and image feature interpretation), while control system design has been limited to ad-hoc strategies or linear single degree-of-freedom (DOF) systems. This dissertation formalizes an analytical approach to dynamic robot visual servo control systems by organizing and categorizing visual control strategies into position-based structures and image-based structures. The image-based structure represents a new approach to visual servo control, which uses image features (e.g., image areas, and centroids) as feedback control signals, thus eliminating a complex interpretation step (i.e., interpretation of image features to derive world-space coordinates). This approach also facilities robot task training by a teach-by-showing strategy for specification of the control system reference signal commands. The dissertation includes an in-depth analysis, design, and evaluation of image-based control. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1984
- Accession Number
- ADA150057
Entities
People
- L. E. Weiss
Organizations
- Carnegie Mellon University