Population-Based Uncalibrated Visual Servoing

Bonković, Mirjana; Hace, A.; Jezernik, K.

doi:10.1109/tmech.2008.924135

Cited by 30 publications

(23 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…control command particle displacement end-effector point end-effector region (motor) no-tool marker pencil pliers wrench single-link robot The new control input A t for the current step is then computed quickly and cheaply using the pseudoinverse of the Jacobian, as A t = ηĴ † t (G − S * (t)), where η is a rate hyperparameter. Once A t is executed and the new position S * is measured, the Jacobian matrix is updated as above, and the process repeats until S * ≈ G. The Broyden update above is susceptible to noise, since it only uses a single ∆S t measurement, hence we apply a batched update comprising the last T tuples of (A τ , ∆S τ ) as proposed in [13]. In our experiments, we set T = 10.…”

Section: B Visual Servoing In Mrcp Coordinatesmentioning

confidence: 99%

Morphology-Agnostic Visual Robotic Control

Yang

Jayaraman

Berseth

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Existing approaches for visuomotor robotic control typically require characterizing the robot in advance by calibrating the camera or performing system identification. We propose MAVRIC, an approach that works with minimal prior knowledge of the robot's morphology, and requires only a camera view containing the robot and its environment and an unknown control interface. MAVRIC revolves around a mutual informationbased method for self-recognition, which discovers visual "control points" on the robot body within a few seconds of exploratory interaction, and these control points in turn are then used for visual servoing. MAVRIC can control robots with imprecise actuation, no proprioceptive feedback, unknown morphologies including novel tools, unknown camera poses, and even unsteady handheld cameras. We demonstrate our method on visuallyguided 3D point reaching, trajectory following, and robot-torobot imitation.

show abstract

Section: B Visual Servoing In Mrcp Coordinatesmentioning

confidence: 99%

Morphology-Agnostic Visual Robotic Control

Yang

Jayaraman

Berseth

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…IBVS includes a special subset where no camera calibration or knowledge of an exact system model (e.g., model-free) is needed, and it offers additional flexibility, especially in unknown and unstructured environments [8,9]. An additional division can be made based on the procedure used for the calculation of an image Jacobian [9,17].…”

Section: Image-based Visual Servoing -A Brief Literature Reviewmentioning

confidence: 99%

“…This paper focuses on an image-based visual servoing (IBVS) approach in which control error is defined in the image plane, enabling the use of an uncalibrated and model-free approach [8,9]. To achieve this, a Jacobian matrix needs to be calculated/estimated to define dependencies between changes in the camera coordinate frame (visual changes) with changes in the robot coordinate frame (robot angle changes).…”

Section: Introductionmentioning

confidence: 99%

“…To achieve this, a Jacobian matrix needs to be calculated/estimated to define dependencies between changes in the camera coordinate frame (visual changes) with changes in the robot coordinate frame (robot angle changes). Since the early 2000s, several approaches to image matrix estimation have emerged based on nonlinear optimization algorithms [8][9][10][11][12] which are a significant improvement on traditional methods for Jacobian estimation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Uncalibrated Model-Free Visual Servoing Methods for Small-Amplitude Movements: A Simulation Study

Musić

Bonković

Cecić

2014

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

The paper compares the performance of several methods used for the estimation of an image Jacobian matrix in uncalibrated model-free visual servoing. This was achieved for an eye-in-hand configuration with small-amplitude movements with several sets of system parameters. The tested methods included the Broyden algorithm, Kalman and particle filters as well as the recently proposed population-based algorithm. The algorithms were tested in a simulation environment (Peter Corke's Robotic Toolbox for MATLAB) on a PUMA 560 robot. Several application scenarios were considered, including static point and dynamic trajectory tracking, with several characteristic shapes and three different speeds. Based on the obtained results, conclusions were drawn about the strengths and weaknesses of each method both for a particular setup and in general. Algorithm-switching was introduced and explored, since it might be expected to improve overall robot tracking performance with respect to the desired trajectory. Finally, possible future research directions are suggested.

show abstract

“…To address the issue of retention of visual features in the camera FOV, an IBVS-based robust grasping system for wheeled mobile robots (WMRs) was developed in [31]. The problem of IBVS in unstructured environments has been addressed in [32] by using the history of iterates to estimate the system Jacobian.…”

Section: Fine Motionmentioning

confidence: 99%

Motion Segmentation and Control Design for UCF-MANUS—An Intelligent Assistive Robotic Manipulator

Kim

Wang

Behal

2012

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

In this paper, we document the progress in the design of a motion segmentation and control strategy for a smart assistive robot arm that can provide assistance during activities of daily living to the elderly and/or users with disabilities. Interaction with the environment is made challenging by the kinematic uncertainty in the robot, imperfect sensor calibration as well as the fact that most activities of daily living are generally required to be performed in unstructured environments. The motion control strategy exploits visual and force feedback from sensors in the robot's hand to provide the basis for efficient interaction with the unstructured environment. Through experimental studies with a variety of objects of daily life in natural environments, an anthropomorphic-like approach was found to be the most suitable for reliable and speedy object retrieval. Specifically, gross reaching/docking motions of the robot arm using proprioception are followed by fine alignment of the hand through visual feedback and eventually grasping based on haptic feedback. Experimental results using a wheelchair mounted robotic arm are presented to demonstrate the efficacy of the proposed algorithms.

show abstract

Population-Based Uncalibrated Visual Servoing

Cited by 30 publications

References 12 publications

Morphology-Agnostic Visual Robotic Control

Morphology-Agnostic Visual Robotic Control

Comparison of Uncalibrated Model-Free Visual Servoing Methods for Small-Amplitude Movements: A Simulation Study

Motion Segmentation and Control Design for UCF-MANUS—An Intelligent Assistive Robotic Manipulator

Contact Info

Product

Resources

About