Parameter identification of unmanned marine vehicle manoeuvring model based on extended Kalman filter and support vector machine

Dong, Zaopeng; Yang, Xiaoxia; Zheng, Mao; Song, Lifei; Mao, Yunsheng

doi:10.1177/1729881418825095

Cited by 28 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, not all robot companies can provide the mass matrix and gravity vector information to users in advance. Recently, a lot of parameter identification methods for the robot dynamics have also been proposed, such as the convex programming approach [19], adaptive control algorithm [20]- [22], extended Kalman filter method [23], neural networks method [24]- [26] and so on. However, the common problem for these methods are that the identification accuracy can not be guaranteed.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Identification of the KUKA LBR iiwa Robot With Retrieval of Physical Parameters Using Global Optimization

Fan

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

This paper focuses on the problem of extracting the physical dynamic parameters which are fundamental for computing the positive-definite link mass matrix. To solve this problem, a minimal set of dynamic parameters were firstly identified by the standard least squares method. In order to simplify the dynamics model, a new set of essential dynamic parameters were calculated by eliminating the poorly identified parameters with an iterative approach. Based on these dynamic parameters with better identification quality, a universally global optimization framework was proposed here to retrieve the set of physical dynamic parameters of a serial robot, in which parameter bounds, linear and nonlinear constraints with physical consistency can be easily considered, such as the triangle inequality of the link inertia tensors, the total link mass limitations, other user-defined constraints and so on. Finally, validation experiments were conducted on the KUKA LBR iiwa 14 R820 robot. The results show that the proposed optimization framework is effective, and the identified dynamic parameters can predict the robot joint torques accurately for the validation trajectories. INDEX TERMS dynamic parameter identification, physical parameters, nonlinear global optimization, KUKA LBR iiwa robot.

show abstract

Section: Introductionmentioning

confidence: 99%

Dynamic Identification of the KUKA LBR iiwa Robot With Retrieval of Physical Parameters Using Global Optimization

Fan

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…2,3 The multi-innovation identification method widens the concept of innovation recognition. 4,5 In Dong et al, 6 a novel identification algorithm was developed by fuse of the extended Kalman filtering and the support-vector machine method. Furthermore, the least square method was proposed by Yang and Guo.…”

Section: Introductionmentioning

confidence: 99%

Nonlinear innovation identification of ship response model via the hyperbolic tangent function

Song

Zhang

2020

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

This research is concerned with the problem of parameter identification for ship response model. A novel nonlinear innovation–based algorithm is proposed by use of the hyperbolic tangent function and the stochastic gradient algorithm. In order to demonstrate the validity of the algorithm, two identification experiments are adopted by the “Galaxy” ship and the “Yupeng” ship. Furthermore, the comparison experiment is illustrated to verify the effectiveness of the proposed algorithm, including the least square algorithm, the traditional stochastic gradient algorithm and the improved nonlinear innovation–based stochastic gradient algorithm. The identification results indicate that the improved stochastic gradient algorithm is with higher accuracy by 95.2% than the original algorithm and 11.75% than the least square algorithm. In addition, the proposed algorithm is with advantages of fast speed and high accuracy of identification. That can be extended to other parameter identification systems with the limited test data.

show abstract

“…Unmanned marine vehicle (UMV), usually contained unmanned/autonomous underwater vehicle (UUV/AUV) and unmanned/autonomous surface vehicle (USV/ASV), can be used to perform a multitude of different tasks, such as mineral resources sampling, offshore oil and gas operations, ocean engineering maintenance, and military reconnaissance, and it is attracting more and more interest from the scientific, commercial, and naval sectors. [1][2][3][4][5] Although much advancements have been realized in this area, the demand for more advantages in navigation, guidance, and control system for UMVs continues to grow, as more and more vehicle autonomy is required. [6][7][8][9][10] In practical implementation, many UMVs are designed of underactuated configurations due to practical considerations, such as reducing weight and/or cost and improving structural strength.…”

Section: Introductionmentioning

confidence: 99%

“…u c and v c are the ocean current velocities, t u and t r are the surge force and yaw moment of UMV, m 11 , m 22 , m 33 , m 23 , and m 32 are UMV's inertia coefficients including added mass effects, and d l 11 , d l 22 , d l 33 , d l 23 , d l 32 are all hydrodynamic linear damping coefficients, while d nl 11 , d nl 22 , d nl 33 , d nl 23 , d nl 32 are all hydrodynamic nonlinear damping coefficients.Expanding system (1) above leads to the UMV's kinematics equations(2) and dynamics equations(3) …”

mentioning

confidence: 99%

Path following control of an underactuated unmanned marine vehicle with model asymmetry in the presence of ocean current disturbances

Zhang

Sun

Zhuang

et al. 2019

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Path following control system of an underactuated unmanned marine vehicle is an important guarantee for its successful operation, the path following control problem of an underactuated and asymmetrical unmanned marine vehicle sailing in the presence of ocean current disturbances is addressed. Asymmetry of the unmanned marine vehicle model and higher order velocity coupling terms of damping coefficients of the unmanned marine vehicle are discussed, which would improve the accuracy of the path following control system. A kind of global differential homeomorphism transformation design is proposed to solve the difficulty of nonzero term appearing in the non-diagonal elements of the system inertia coefficient matrix and damping coefficient matrix, which is caused by the model asymmetry of unmanned marine vehicle. An improved line-of-sight guidance algorithm is presented by introducing longitudinal position error and tracking error weight factor into traditional line-of-sight algorithm, which could speed up the path following process, meanwhile the method could be extended to the application of curve path following. Virtual velocity in the tangent direction of the path to be followed is designed for the control system, by increasing a virtual control input, the underactuated control system is simplified, and the higher order velocity coupling terms of damping coefficients are integrated considered in the virtual control law. Stability of the path following control algorithm proposed for unmanned marine vehicle is proved by Lyapunov theory, and some simulation experiments are carried out to verify the effectiveness of the path following control system designed.

show abstract

Parameter identification of unmanned marine vehicle manoeuvring model based on extended Kalman filter and support vector machine

Cited by 28 publications

References 30 publications

Dynamic Identification of the KUKA LBR iiwa Robot With Retrieval of Physical Parameters Using Global Optimization

Dynamic Identification of the KUKA LBR iiwa Robot With Retrieval of Physical Parameters Using Global Optimization

Nonlinear innovation identification of ship response model via the hyperbolic tangent function

Path following control of an underactuated unmanned marine vehicle with model asymmetry in the presence of ocean current disturbances

Contact Info

Product

Resources

About