Improved Noise Covariance Estimation in Visual Servoing Using an Autocovariance Least-squares Approach

Brown, Jasper; Su, Daobilige; Kong, He; Sukkarieh, Salah; Kerrigan, Eric C.

doi:10.1016/j.ifacol.2019.11.044

Cited by 5 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For improving the disturbance rejection performance, Qiu et al (2020) propose an adaptive model predictive control approach, which is based on a modified disturbance observer, enhancing the robustness of the servoing system to external disturbances. Regarding to the model-based visual servoing, Brown et al (2020) utilize the autocovariance least-squares scheme to identify the covariance of the pose estimation with both the positive semi-definiteness and the desired structural constraints. Shi et al (2020) extend the bagging method to calculate the inverse kinematics to the controller rather than the Moore-Penrose pseudoinverse, thus reducing the influence of the image noise to the controller.…”

Section: External Disturbance and Image Noisementioning

confidence: 99%

A survey on visual servoing for wheeled mobile robots

Wang

et al. 2021

Int J Intell Robot Appl

View full text Add to dashboard Cite

Owing to advantages of large workspace and flexible movement, wheeled mobile robots are widely applied in industry. With vision module for environment perception, visual servoing of wheeled mobile robots has been one of the hottest research topics in robotic fields. Due to different demands for various applications and specific properties of the system, many challenges are faced for designing visual servoing control strategies. In this paper, development of visual servoing for mobile robots is elaborated in visual and control modules, respectively. The vision module along with various uncertainties are analyzed, which provides feedback signals for the servo controller, thus associating the image space with the motion space for further control. Moreover, motion controllers are devised under various constraints for different objectives, such as pose regulation and trajectory tracking. Research trends are discussed to show further focus of visual servoing of mobile robots.

show abstract

Section: External Disturbance and Image Noisementioning

confidence: 99%

A survey on visual servoing for wheeled mobile robots

Wang

et al. 2021

Int J Intell Robot Appl

View full text Add to dashboard Cite

show abstract

“…The EKF state vector, default noise matrices and initial covariance matrix are given by

s t a t e = (][, \begin{matrix} x_{1} \\ y_{1} \\ z_{1} \\ x_{2} \\ y_{2} \\ ⋮ \\ z_{n} \end{matrix}), Q = 0.01 \times ℐ_{n, n}, R = 0.02 \times ℐ_{n, n}, P = (][, \begin{matrix} 0.05 & 0 & 0 \\ 0 & 0.05 & 0 \\ 0 & 0 & 0.1 \end{matrix}),

where

MJX-tex-caligraphicnormalℐ

is the identity matrix and

n

is the number of fruit currently being tracked. A method for estimating these noise covariance matrices is presented in our previous work (Brown, Su, Kong, Sukkarieh, & Kerrigan, 2019). All units are in meters and the third element of

P

is aligned with the camera depth axis ( d ) under our frame definitions, so has greater variance than the ( u , v ) pixel readings.…”

Section: Software and Algorithm Designmentioning

confidence: 99%

Design and evaluation of a modular robotic plum harvesting system utilizing soft components

Brown

Sukkarieh

2020

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

The human labor required for tree crop harvesting is a major cost component in fruit production and is increasing. To address this, many existing research works have sought to demonstrate commercially viable robotic harvesting for tree crops, though successful commercial products resulting from these have been few and far between. Systems developed for specific crops such as sweet peppers or apples have shown promise, but the vast majority of cultivar types remain unaddressed, and developing a specific system for each one is inefficient. In this study, an easily modifiable development platform for robotic fruit harvesting is presented, this can be used to test specific design choices on different fruit and growing conditions. The system is evaluated in a commercial plum orchard, with no crop modifications. Both a hard and soft gripper are trialed, along with three object detector approaches and two picking motions. Some existing techniques are found to be counterproductive for plums, while soft robotics and persistent target tracking significantly improve performance. The best harvest success rate of 42%, was observed when using the soft gripper with complex motion. This is lower than expected based on prior testing with apples and indicates the difficulty in moving to new fruit types. Unique challenges specific to the plum type and growing style are examined in the context of system module design choices.

show abstract

“…where I is the identity matrix. A method for estimating these noise covariance matrices is presented in our previous work (Brown, Su, Kong, Sukkarieh & Kerrigan, 2019). All units are in meters and the third element of P is aligned with the camera depth axis (d) under our frame definitions, so has greater variance than the (u,v) pixel readings.…”

Section: Perceptionmentioning

confidence: 99%

Design and Evaluation of a Modular Robotic Plum Harvesting System Utilising Soft Components

Brown,

Sukkarieh

2020

Preprint

Self Cite

View full text Add to dashboard Cite

The human labour required for tree crop harvesting is a major cost component in fruit production and is increasing. To address this, many existing research works have sought to demonstrate commercially viable robotic harvesting for tree crops, though successful commercial products resulting from these have been few and far between. Systems developed for specific crops such as sweet peppers or apples have shown promise, but the vast majority of cultivar types remain unaddressed and developing a specific system for each one is inefficient. In this work a flexible and modular development platform is presented, this can be used to test specific design choices on different fruit and growing conditions. The system is evaluated in a commercial plum orchard, with no crop modifications. Some existing techniques are found to be counterproductive for plums, while soft robotics and persistent target tracking significantly improve performance. A harvest success rate of 42% was observed, with lower than expected effectiveness based on prior testing with apples. The plum type and growing style pose unique challenges which are examined in the context of system module design choices.

show abstract

Improved Noise Covariance Estimation in Visual Servoing Using an Autocovariance Least-squares Approach

Cited by 5 publications

References 19 publications

A survey on visual servoing for wheeled mobile robots

A survey on visual servoing for wheeled mobile robots

Design and evaluation of a modular robotic plum harvesting system utilizing soft components

Design and Evaluation of a Modular Robotic Plum Harvesting System Utilising Soft Components

Contact Info

Product

Resources

About