Strategies for Increasing the Tracking Region of an Eye-in-Hand System by Singularity and Joint Limit Avoidance

Abstract

An eye-in-hand system visually tracking objects can fail when the manipulator encounters a kinematic singularity or a joint limit. A solution to this problem is presented in which objects are visually tracked while the manipulator simultaneously avoids kinematic singularities and manipulator joint limits by moving in directions along which the tracking task space is unconstrained or redundant. A manipulability measure is introduced into the visual tracking objective function, providing an elegant and robust technique for deriving a control law that visually tracks objects while accounting for the configuration of the manipulator. Two different tracking strategies, one using a standard visual tracking strategy and the other using the newly proposed strategy, are experimentally compared on an actual hand/eye system. The experimental results demonstrate the effectiveness of the new method by showing that the tracking region of a manipulator tracking objects with planar motion can be greatly increased.

A novel framework for closed-loop robotic motion simulation - part I: Inverse kinematics design

“…The same applies to the avoidance of singularities where suitable indexes, such as the manipulability measure [18], can be optimized. Mixed solutions, i.e., concurrent avoidance of joint limits and singularities, have also been explored [19], as well as strategies to soften the effect of singularities when passing close to them [14], [20].…”

Active vision for complete scene reconstruction and exploration

“…This estimation requires camera motions performed by visual servoing which can not be realized if the robot encounters a joint limit. The measure % related to this constraint (and similar to those proposed in [13] or [17]) is optimal (equal to 0) if the camera is located at the middle of the extension of each axis of the robot: …”

Avoiding self-occlusions and preserving visibility by path planning in the image

“…Both self-occlusions and visibility constraints are taken into account. Contrary to others approaches [2,15] exploiting the robot redundancy, the self-occlusions and visibility constraints can be ensured even if all the robot degrees of freedom are used to realize the task.…”