Robot visual servo through trajectory estimation of a moving object using kalman filter
16 Sep 2009-pp 1122-1130
TL;DR: The robot visual servo control algorithm is simulated, implemented and discussed with a Samsung FARA AT-2 robot and a MV50 Camera for its effectiveness, in both cases of with/without a trajectory estimation algorithm of a moving object using Kalman filter.
Abstract: In this paper, a robot visual servo control algorithm is proposed by combining the conventional image based robot visual servoing algorithm with a trajectory estimation algorithm of a moving object using Kalman filter. The erroneous image information of a moving object due to the imprecise camera characteristics is compensated by applying Kalman filter to the process model of a moving object. The robot visual servo control algorithm is simulated, implemented and discussed with a Samsung FARA AT-2 robot and a MV50 Camera for its effectiveness, in both cases of with/without a trajectory estimation algorithm of a moving object using Kalman filter.
Citations
More filters
28 Jul 2014
TL;DR: An image-based eye-in-hand stereo visual servoing system for a stereo vision system mounted on the end-effector of 6 degrees of freedom (DOF) robot to perform a task of tracking and catching a moving object in real time.
Abstract: In this paper an image-based eye-in-hand stereo visual servoing system is proposed to perform a task of tracking and catching a moving object in real time. The presented method utilizes the conventional image based visual servoing algorithm for a stereo vision system mounted on the end-effector of 6 degrees of freedom (DOF) robot. In order to estimate the object motion trajectory in two dimensional image planes and predict the future positions, a Kalman filter with a linear model of the moving object and also an extended Kalman filter (EKF) with a non-linear model are employed. The procedure of tracking and catching a moving object is simulated and implemented based on a 6 DOF DENSO 6242G robot. Both simulation and experimental results are presented to verify the effectiveness of the proposed methods. The comparison with the case of a monocular image-based system is carried out.
12 citations
Cites methods from "Robot visual servo through trajecto..."
...Using IBVS, robotic catching of moving objects has been achieved successfully in a few efforts [16, 17]....
[...]
Dissertation•
15 Mar 2013
TL;DR: A stereo Image-based Visual Servoing (IBVS) with eye‐in‐hand configuration with eye-in-hand configuration that is able to track and grasp a moving object in real time and a method for position prediction and trajectory estimation of the moving tar-get for a real-time grasping task is introduced.
Abstract: Robotic systems have been increasingly employed in various industrial, urban, mili-tary and exploratory applications during last decades. To enhance the robot control per-formance, vision data are integrated into the robot control systems. Using visual feedback has a great potential for increasing the flexibility of conventional robotic and mechatronic systems to deal with changing and less-structured environments. How to use visual in-formation in control systems has always been a major research area in robotics and mechatronics. Visual servoing methods which utilize direct feedback from image features to motion control have been proposed to handle many stability and reliability issues in vision-based control systems.
This thesis introduces a stereo Image-based Visual Servoing (IBVS) (to the contrary Position-based Visual Servoing (PBVS)) with eye‐in‐hand configuration that is able to track and grasp a moving object in real time. The robustness of the control system is in-creased by the means of accurate 3-D information extracted from binocular images. At first, an image-based visual servoing (IBVS) approach based on stereo vision is proposed for 6 DOF robots. A classical proportional control strategy has been designed and the ste-reo image interaction matrix which relates the image feature velocity to the cameras’ ve-locity screw has been developed for two cases of parallel and non-parallel cameras in-stalled on the end-effector of the robot. Then, the properties of tracking a moving target and corresponding variant feature points on visual servoing system has been investigated.
Second, a method for position prediction and trajectory estimation of the moving tar-get in order to use in the proposed image-based stereo visual servoing for a real-time grasping task has been proposed and developed through the linear and nonlinear model-ing of the system dynamics. Three trajectory estimation algorithms, “Kalman Filter”, “Recursive Least Square (RLS)” and “Extended Kalman Filter (EKF)” have been applied to predict the position of moving object in image planes.
Finally, computer simulations and real implementation have been carried out to verify the effectiveness of the proposed method for the task of tracking and grasping a moving object using a 6-DOF manipulator.
8 citations
Cites background from "Robot visual servo through trajecto..."
...13 A manipulator robot trying to track and catch a moving object [44]...
[...]
...13 A manipulator robot trying to track and catch a moving object [44] ....
[...]
01 Sep 2020
TL;DR: This paper circumvents the problem of tracking an unknown maneuvering target using only monocular visual feedback using the angle subtended by the target on the follower in both 3D and image coordinate systems.
Abstract: This paper delves into the problem of tracking an unknown maneuvering target using only monocular visual feedback. It is usually difficult to perform target tracking using only monocular vision due to the absence of depth information. This restricts the use of commonly used Image and Position-based Visual Servoing methods. Hence, range estimation from monocular images has paramount importance if a conventional position based path planning algorithm is to be utilized. In this paper, we circumvent this problem using the angle subtended by the target on the follower in both 3D and image coordinate systems. Also, an Extended Kalman Filter is used to filter and get accurate range estimates of the moving target. The proposed method is extensively validated on a simulated setup created in Gazebo. Also, a Proportional Derivative (PD) controller is used to maintain a fixed standoff distance from the moving target while following it.
4 citations
Cites methods from "Robot visual servo through trajecto..."
...Koh et al [12] also used an IBVS approach by combining it with a trajectory estimation algorithm of a moving object using a Kalman Filter....
[...]
01 Jun 2018
TL;DR: The use of traditional Kalman filter is incorporated to estimate the position and the trajectory of the single object in motion to generate improved results with high convergence rate and low tracking error compared toKalman filter.
Abstract: The application of Kalman Filter in the process of state estimation and thereby tracking a single object in motion is explored in this paper. A collection of images consisting of 200 different instances of the single object's position has been taken into consideration, whose location has been found with the help of background subtraction technique. The actual trajectory has been obtained by connecting the centroid locations of the obtained images of moving object. This paper incorporates the use of traditional Kalman filter to estimate the position and the trajectory of the single object in motion. The performance of the traditional Kalman filter has also been compared with a proposed modified version of Kalman filter for this challenging job. An exponential function has been multiplied with the Kalman gain in the modified Kalman filter. The performance evaluation shows that the modified Kalman filter generates improved results with high convergence rate and low tracking error compared to Kalman filter. The work presented here has enormous potential in the field of object tracking and navigation for different practical applications.
2 citations
Cites background from "Robot visual servo through trajecto..."
...The incorporation of robotic vision and its servo control provide the robot with the idea of the surrounding environment, which boost its work and efficiency [2]....
[...]
15 Nov 2011
TL;DR: In this article, a polynomial interpolation technique is used to generate the trajectory in order to intercept two or more moving objects in an industrial environment, such as objects moving on a circular or linear conveyor.
Abstract: This paper presents a novel methodology based on polynomial-interpolation technique to generate the trajectory in order to intercept two or more moving objects. This methodology is efficient for the slowmaneuvering objects with constant acceleration in industrial settings, like objects moving on a circular or linear conveyor. The position, velocity and acceleration as a function of time of the free-particles are used as input to the methodology. With this kinematic information is possible to generate the multiple interception trajectory. The multiple interception trajectory allows to the endeffector of a robotic arm to be oriented along each of the free particle's-trajectory to avoid impact due to the direction of their velocities. The implementation of the proposing methodology is ilustrated through a simulation examples, which consist of the interception of two objects moving along a well-known trajectory via two degrees of freedom robot arm. The endeffector tracking the desired follower-trajectory to intercept two moving objects in the task space.
1 citations
References
More filters
01 Oct 1987
TL;DR: Simulation studies of two- and three-degree-of-freedom systems show the application of an adaptive control algorithm to overcome unknown and nonlinear relations in the feature to world space mapping.
Abstract: Sensor-based robot control may be viewed as a hierarchical structure with multiple observers. Actuator, feature-based, and recognition observers provide the basis for multilevel feedback control at the actuator, sensor, and world coordinate frame levels, respectively. The analysis and design of feature-based control strategies to achieve consistent dynamic performance is addressed. For vision sensors, such an image-based visual servo control is shown to provide stable and consistent dynamic control within local regimes of the recognition observer. Simulation studies of two- and three-degree-of-freedom systems show the application of an adaptive control algorithm to overcome unknown and nonlinear relations in the feature to world space mapping.
889 citations
"Robot visual servo through trajecto..." refers background in this paper
...In order to allow a robot to have more flexibility and more precision for the various tasks, the robot visual servo control (or robot visual servoing) has been investigated by many researchers[ 1-5 ]....
[...]
01 Oct 1993
TL;DR: This paper attempts to present a comprehensive summary of research results in the use of visual information to control robot manipulators and related mechanisms in terms of historical context, common-ality of function, algorithmic approach and method of implementation.
Abstract: This paper attempts to present a comprehensive summary of research results in the use of visual information to control robot manipulators and related mechanisms. An extensive bibliography is provided which also includes important papers from the elemental disciplines upon which visual servoing is based. The research results are discussed in terms of historical context, common-ality of function, algorithmic approach and method of implementation.
355 citations
"Robot visual servo through trajecto..." refers background or methods in this paper
...Position based control uses the error measured in 3 dimensional Cartesian space, while image based control uses the error in 2 dimensional image plane[ 2 ]....
[...]
...In order to allow a robot to have more flexibility and more precision for the various tasks, the robot visual servo control (or robot visual servoing) has been investigated by many researchers[ 1-5 ]....
[...]
TL;DR: Results of an experiment with real imagery are presented, involving estimation of 28 unknown translational, rotational, and structural parameters, based on 12 images with seven feature points.
Abstract: The problem considered involves the use of a sequence of noisy monocular images of a three-dimensional moving object to estimate both its structure and kinematics. The object is assumed to be rigid, and its motion is assumed to be smooth. A set of object match points is assumed to be available, consisting of fixed features on the object, the image plane coordinates of which have been extracted from successive images in the sequence. Structure is defined as the 3-D positions of these object feature points, relative to each other. Rotational motion occurs about the origin of an object-centered coordinate system, while translational motion is that of the origin of this coordinate system. In this work, which is a continuation of the research done by the authors and reported previously (ibid., vol.PAMI-8, p.90-9, Jan. 1986), results of an experiment with real imagery are presented, involving estimation of 28 unknown translational, rotational, and structural parameters, based on 12 images with seven feature points. >
200 citations
"Robot visual servo through trajecto..." refers methods in this paper
...In order to relieve this problem, Chang[6] suggested 3 dimensional motion parameter estimation method for tracking a maneuvering target with Kalman filter, Broida and Chellappa[ 7 ] suggests a dynamic model of a rigid object with Kalman filter....
[...]
11 May 2002
TL;DR: A novel approach is presented in order to guarantee that the object remains in the field of view of the camera during the whole robot motion, which consists in tracking an iteratively computed trajectory.
Abstract: Visual servoing requires an object in the field of view of the camera, in order to control the robot evolution. Otherwise, the virtual link is broken and the control loop cannot continue to be closed. In this paper, a novel approach is presented in order to guarantee that the object remains in the field of view of the camera during the whole robot motion. It consists in tracking an iteratively computed trajectory. A position based modeling adapted to a moving target object is established, and is used to control the trajectory. A nonlinear decoupling approach is then used to control the robot. Experiments, demonstrating the capabilities of this approach, have been conducted on a Cartesian robot connected to a real time vision system, with a CCD camera mounted on the end effector of the robot.
186 citations
"Robot visual servo through trajecto..." refers background in this paper
...In order to allow a robot to have more flexibility and more precision for the various tasks, the robot visual servo control (or robot visual servoing) has been investigated by many researchers[ 1-5 ]....
[...]
01 Sep 1990
TL;DR: An adaptive method for visually tracking a known moving object with a single mobile camera to predict the location of features of the object on the image plane based on past observations and past control inputs and to determine an optimal control input that will move the camera so that the image features align with their desired positions.
Abstract: An adaptive method for visually tracking a known moving object with a single mobile camera is described. The method differs from previous methods of motion estimation in that both the camera and the object are moving. The objective is to predict the location of features of the object on the image plane based on past observations and past control inputs and then to determine an optimal control input that will move the camera so that the image features align with their desired positions. A resolved motion rate control structure is used to control the relative position and orientation between the camera and the object. A geometric model of the camera is used to determine the linear differential transformation from image features to camera position and orientation. To adjust for modeling errors and system nonlinearities, a self-tuning adaptive controller is used to update the transformation and compute the optimal control. Computer simulations were conducted to verify the performance of the adaptive feature prediction and control. >
171 citations