Implementations of Robot Visual Servo by Learning

Zhao, Qingjie; Deng, Hongbin; Duan, Xingguang; Hu, Haidong

doi:10.1109/icicic.2008.314

Cited by 2 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the IBVS control system in Fig. 1, given the desired position of the image feature point on the image plane, and applying the proposed controller (12), the image error is convergent to zero, i.e., e → 0, as time tends to infinity.…”

Section: Image-based Visual Servo Control Systemmentioning

confidence: 98%

“…Bonković et al [11] suggested an approach using a radial basis function network to learn the visual-motor coordination. Zhao et al [12] used a wavelet function neural network to acquire the complicated nonlinear relation between the image features and the robot control commands. Li et al [13] used a back-propagation neural network to map the transformation from image moments variation to the robot pose displacement without the external and internal parameters calibration for camera.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Design of robotic visual servo control based on neural network and genetic algorithm

Hong-bin

Liu

2012

Int. J. Autom. Comput.

View full text Add to dashboard Cite

A new visual servo control scheme for a robotic manipulator is presented in this paper, where a back propagation (BP) neural network is used to make a direct transition from image feature to joint angles without requiring robot kinematics and camera calibration. To speed up the convergence and avoid local minimum of the neural network, this paper uses a genetic algorithm to find the optimal initial weights and thresholds and then uses the BP algorithm to train the neural network according to the data given. The proposed method can effectively combine the good global searching ability of genetic algorithms with the accurate local searching feature of BP neural network. The Simulink model for PUMA560 robot visual servo system based on the improved BP neural network is built with the Robotics Toolbox of Matlab. The simulation results indicate that the proposed method can accelerate convergence of the image errors and provide a simple and effective way of robot control.

show abstract

Section: Image-based Visual Servo Control Systemmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Design of robotic visual servo control based on neural network and genetic algorithm

Hong-bin

Liu

2012

Int. J. Autom. Comput.

View full text Add to dashboard Cite

show abstract

“…Therefore, people began to seek new methods to achieve robot-tracking dynamic targets. Currently, the commonly used dynamic target tracking methods include the direct targeting method [5], the pyramid optimization method [6], the proportional guidance method [7], and the visual servo method [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Trajectory Planning for Coal Gangue Sorting Robot Tracking Fast-Mass Target under Multiple Constraints

Wang

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

Aiming at the problems of grab failure and manipulator damage, this paper proposes a dynamic gangue trajectory planning method for the manipulator synchronous tracking under multi-constraint conditions. The main reason for the impact load is that there is a speed difference between the end of the manipulator and the target when the manipulator grabs the target. In this method, the mathematical model of seven-segment manipulator trajectory planning is constructed first. The mathematical model of synchronous tracking of dynamic targets based on a time-minimum manipulator is constructed by taking the robot’s acceleration, speed, and synchronization as constraints. The model transforms the multi-constraint-solving problem into a single-objective-solving problem. Finally, the particle swarm optimization algorithm is used to solve the model. The calculation results are put into the trajectory planning model of the manipulator to obtain the synchronous tracking trajectory of the manipulator. Simulation and experiments show that each joint of the robot’s arm can synchronously track dynamic targets within the constraint range. This method can ensure the synchronization of the position, speed, and acceleration of the moving target and the target after tracking. The average position error is 2.1 mm, and the average speed error is 7.4 mm/s. The robot has a high tracking accuracy, which further improves the robot’s grasping stability and success rate.

show abstract

Implementations of Robot Visual Servo by Learning

Cited by 2 publications

References 9 publications

Design of robotic visual servo control based on neural network and genetic algorithm

Design of robotic visual servo control based on neural network and genetic algorithm

Trajectory Planning for Coal Gangue Sorting Robot Tracking Fast-Mass Target under Multiple Constraints

Contact Info

Product

Resources

About