A Novel Image-based Path Planning Algorithm for Eye-in-Hand Visual Servoing of a Redundant Manipulator in a Human Centered Environment
01 Oct 2019-pp 1-8
TL;DR: A novel image-based path-planning and execution framework for vision-based control of a robot in a human centered environment that eliminates many of the inherent limitations of IBVS with eye-in-hand configuration and makes the use of visual servoing practical for dynamic and complex environments.
Abstract: This paper presents a novel image-based path-planning and execution framework for vision-based control of a robot in a human centered environment. The proposed method involves applying Rapidly-exploring Random Tree (RRT) exploration to perform Image-Based Visual Servoing (IBVS) while satisfying multiple task constraints by exploiting robot redundancy. The methodology incorporates data-set of robot’s workspace images for path-planning and design a controller based on visual servoing framework. This method is generic enough to include constraints like Field-of-View (FoV) limits, joint limits, obstacles, various singularities, occlusions etc. in the planning stage itself using task function approach and thereby avoiding them during the execution. The use of path-planning eliminates many of the inherent limitations of IBVS with eye-in-hand configuration and makes the use of visual servoing practical for dynamic and complex environments. Several experiments have been performed on a UR5 robotic manipulator to demonstrate that it is an effective and robust way to guide a robot in such environments.
References
More filters
01 Oct 1996
TL;DR: This article provides a tutorial introduction to visual servo control of robotic manipulators by reviewing the prerequisite topics from robotics and computer vision, including a brief review of coordinate transformations, velocity representation, and a description of the geometric aspects of the image formation process.
Abstract: This article provides a tutorial introduction to visual servo control of robotic manipulators. Since the topic spans many disciplines our goal is limited to providing a basic conceptual framework. We begin by reviewing the prerequisite topics from robotics and computer vision, including a brief review of coordinate transformations, velocity representation, and a description of the geometric aspects of the image formation process. We then present a taxonomy of visual servo control systems. The two major classes of systems, position-based and image-based systems, are then discussed in detail. Since any visual servo system must be capable of tracking image features in a sequence of images, we also include an overview of feature-based and correlation-based methods for tracking. We conclude the tutorial with a number of observations on the current directions of the research field of visual servo control.
3,619 citations
"A Novel Image-based Path Planning A..." refers background in this paper
...Visual Servoing (VS) [1] or hand-eye coordination control [2] concerns itself with guiding the robot using visual feedback....
[...]
01 Jun 1997
TL;DR: A new task-priority redundancy resolution technique is developed that overcomes the effects of algorithmic singularities and is applied to a seven-degree-of-freedom manipulator in numerical case studies to demonstrate its effectiveness.
Abstract: Practical application of the task-priority redundancy resolution technique must deal with the occurrence of kinematic and algorithmic singularities. The aim of this paper is twofold. First, the application of existing singularity-robust methods to the case of kinematically redundant arms is studied. Then, a new task-priority redundancy resolution technique is developed that overcomes the effects of algorithmic singularities. Computational aspects of the solutions are also considered in view of real-time implementation of a kinematic control algorithm. The method is applied to a seven-degree-of-freedom manipulator in numerical case studies to demonstrate its effectiveness.
647 citations
"A Novel Image-based Path Planning A..." refers methods in this paper
...To find the corresponding configuration in joint space, a unique mapping between the feature space and the six-dimensional joint space is established by task-priority method [13]....
[...]
...The Task function approach [13] is used which uses 3DoFs for completion of visual servoing task whereas redundant DoFs are used for completion of secondary task....
[...]
TL;DR: Improvements in image-based visual servo using image moments are presented, and the analytical form of the interaction matrix related to the moments computed from a set of coplanar points is derived.
Abstract: Moments are generic (and usually intuitive) descriptors that can be computed from several kinds of objects, defined either from closed contours or from a set of points. In this paper, we present improvements in image-based visual servo using image moments. First, the analytical form of the interaction matrix related to the moments computed from a set of coplanar points is derived, and we show that it is different from the form obtained previously, using coplanar closed contours. Six visual features are selected to design a decoupled control scheme when the object is parallel to the image plane. This nice property is then generalized to the case where the desired object position is not parallel to the image plane. Finally, experimental results are presented to illustrate the validity of our approach and its robustness, with respect to modeling errors.
317 citations
"A Novel Image-based Path Planning A..." refers background or methods in this paper
...In our framework, the image moment-based features have been used during the exploration phase because of its many practical advantages over other features [14], [15]....
[...]
...Here, Lm represents the interaction matrix [14] which contains information about the vision systems and Jg is the Jacobian matrix for robot....
[...]
TL;DR: This paper proposes a kinematic control strategy which enforces safety, while maintaining the maximum level of productivity of the robot.
Abstract: New paradigms in industrial robotics no longer require physical separation between robotic manipulators and humans. Moreover, in order to optimize production, humans and robots are expected to collaborate to some extent. In this scenario, involving a shared environment between humans and robots, common motion generation algorithms might turn out to be inadequate for this purpose.
306 citations
"A Novel Image-based Path Planning A..." refers methods in this paper
...The images from a data-set of real images of robot’s workspace are used for random node generation in RRT instead of numerical random feature generation methods because random synthetic image generation from camera positions is not suitable for real-world applications which uses IBVS framework [12]....
[...]
TL;DR: The theory and implementation of a system that positions a robot manipulator using visual information from two cameras is described, and a control law that moves the robot to drive this error to zero is derived.
Abstract: This article describes the theory and implementation of a system that positions a robot manipulator using visual information from two cameras. The system simultaneously tracks the robot end-effector and visual features used to define goal positions. An error signal based on the visual distance between the end-effector and the target is defined, and a control law that moves the robot to drive this error to zero is derived. The control law has been integrated into a system that performs tracking and stereo control on a single processor with no special-purpose hardware at real-time rates. Experiments with the system have shown that the controller is so robust to calibration error that the cameras can be moved several centimeters and rotated several degrees while the system is running with no adverse effects. >
186 citations
"A Novel Image-based Path Planning A..." refers background in this paper
...Visual Servoing (VS) [1] or hand-eye coordination control [2] concerns itself with guiding the robot using visual feedback....
[...]