Authors:
Tiantian Shen
and
Graziano Chesi
Affiliation:
University of Hong Kong, Hong Kong
Keyword(s):
Sphere, Path-planning, Visual Servoing.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Engineering Applications
;
Formal Methods
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Planning and Scheduling
;
Robotics and Automation
;
Signal Processing, Sensors, Systems Modeling and Control
;
Simulation and Modeling
;
Symbolic Systems
Abstract:
This paper proposes a path-planning approach for visual servoing in the case where the observed object features are points and spheres. Two main situations are considered. In the first situation, it is supposed that at least two points and at least a sphere are observed. In the second situation, it is supposed that at least three spheres are observed. The problem consists of planning a trajectory in order to ensure the convergence of the robot end-point to the desired location while satisfying visibility and workspace constraints, in particular including occlusion and collision avoidance. A solution based on polynomial parametrizations is proposed in order to determine a feasible path in the 3D space, and such a path is then followed by tracking its image projection through image-based visual servoing. Some simulation results illustrate the proposed approach.