151. Autonomous robotic capture of non-cooperative target by adaptive extended Kalman filter based visual servo.
- Author
-
Dong, Gangqi and Zhu, Zheng H.
- Subjects
- *
KALMAN filtering , *ROBOTICS , *KINEMATICS , *MOTION estimation (Signal processing) , *CLOSED loop systems - Abstract
This paper presents a real-time, vision-based algorithm for the pose and motion estimation of non-cooperative targets and its application in visual servo robotic manipulator to perform autonomous capture. A hybrid approach of adaptive extended Kalman filter and photogrammetry is developed for the real-time pose and motion estimation of non-cooperative targets. Based on the pose and motion estimates, the desired pose and trajectory of end-effector is defined and the corresponding desired joint angles of the robotic manipulator are derived by inverse kinematics. A close-loop visual servo control scheme is then developed for the robotic manipulator to track, approach and capture the target. Validating experiments are designed and performed on a custom-built six degrees of freedom robotic manipulator with an eye-in-hand configuration. The experimental results demonstrate the feasibility, effectiveness and robustness of the proposed adaptive extended Kalman filter enabled pose and motion estimation and visual servo strategy. [ABSTRACT FROM AUTHOR]
- Published
- 2016
- Full Text
- View/download PDF