Hybrid pso-newton-raphson algorithm for inverse kinematics problem in robotics
Само за регистроване кориснике
2021
Конференцијски прилог (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Newton-Raphson method is a deterministic numerical method for solving a system of nonlinear equations. In robotics, it is used to solve inverse kinematics problems. In order to converge towards the optimal solution, the Newton-Raphson method requires a good initial value guess, which can be challenging to obtain. The Particle Swarm Optimization (PSO) algorithm is a stochastic optimization technique for solving nonlinear problems. The advantage of the PSO, in this case, is its ability to search a large amount of data. The PSO can narrow down potential solutions close to the optimal solution and use them as an initial guess for the Newton-Raphson method. Then, the Newton-Raphson method takes over and converges towards the desired optimal solution. In this paper, the feasibility of the hybrid PSO-Newton-Raphson algorithm for solution of robot inverse kinematics problem is investigated for a six-degree of freedom robot arm. All six joints of the robot arm are revolute. The cost function fo...r the PSO algorithm is formed as a function of error between the desired and actual position of the robot arm end-effector. The numerical simulation is carried out to verify the applicability of the proposed concept.
Кључне речи:
Inverse kinematics / particle swarm optimization / robot / nonlinear numerical methodИзвор:
Book of abstracts, International Conference of Experimental and Numerical Investigations and New Technologies CNN TECH 2021 46, 2021, 46-46Издавач:
- Beograd : Inovacioni centar Masinskog fakulteta
Финансирање / пројекти:
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200105 (Универзитет у Београду, Машински факултет) (RS-MESTD-inst-2020-200105)
- Министарство науке, технолошког развоја и иновација Републике Србије, институционално финансирање - 200066 (Лола институт, Београд) (RS-MESTD-inst-2020-200066)
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Zivković, Nikola Lj. AU - Vidaković, Jelena AU - Lazarević, Mihailo PY - 2021 UR - https://machinery.mas.bg.ac.rs/handle/123456789/4089 AB - Newton-Raphson method is a deterministic numerical method for solving a system of nonlinear equations. In robotics, it is used to solve inverse kinematics problems. In order to converge towards the optimal solution, the Newton-Raphson method requires a good initial value guess, which can be challenging to obtain. The Particle Swarm Optimization (PSO) algorithm is a stochastic optimization technique for solving nonlinear problems. The advantage of the PSO, in this case, is its ability to search a large amount of data. The PSO can narrow down potential solutions close to the optimal solution and use them as an initial guess for the Newton-Raphson method. Then, the Newton-Raphson method takes over and converges towards the desired optimal solution. In this paper, the feasibility of the hybrid PSO-Newton-Raphson algorithm for solution of robot inverse kinematics problem is investigated for a six-degree of freedom robot arm. All six joints of the robot arm are revolute. The cost function for the PSO algorithm is formed as a function of error between the desired and actual position of the robot arm end-effector. The numerical simulation is carried out to verify the applicability of the proposed concept. PB - Beograd : Inovacioni centar Masinskog fakulteta C3 - Book of abstracts, International Conference of Experimental and Numerical Investigations and New Technologies CNN TECH 2021 46 T1 - Hybrid pso-newton-raphson algorithm for inverse kinematics problem in robotics EP - 46 SP - 46 UR - https://hdl.handle.net/21.15107/rcub_machinery_4089 ER -
@conference{ author = "Zivković, Nikola Lj. and Vidaković, Jelena and Lazarević, Mihailo", year = "2021", abstract = "Newton-Raphson method is a deterministic numerical method for solving a system of nonlinear equations. In robotics, it is used to solve inverse kinematics problems. In order to converge towards the optimal solution, the Newton-Raphson method requires a good initial value guess, which can be challenging to obtain. The Particle Swarm Optimization (PSO) algorithm is a stochastic optimization technique for solving nonlinear problems. The advantage of the PSO, in this case, is its ability to search a large amount of data. The PSO can narrow down potential solutions close to the optimal solution and use them as an initial guess for the Newton-Raphson method. Then, the Newton-Raphson method takes over and converges towards the desired optimal solution. In this paper, the feasibility of the hybrid PSO-Newton-Raphson algorithm for solution of robot inverse kinematics problem is investigated for a six-degree of freedom robot arm. All six joints of the robot arm are revolute. The cost function for the PSO algorithm is formed as a function of error between the desired and actual position of the robot arm end-effector. The numerical simulation is carried out to verify the applicability of the proposed concept.", publisher = "Beograd : Inovacioni centar Masinskog fakulteta", journal = "Book of abstracts, International Conference of Experimental and Numerical Investigations and New Technologies CNN TECH 2021 46", title = "Hybrid pso-newton-raphson algorithm for inverse kinematics problem in robotics", pages = "46-46", url = "https://hdl.handle.net/21.15107/rcub_machinery_4089" }
Zivković, N. Lj., Vidaković, J.,& Lazarević, M.. (2021). Hybrid pso-newton-raphson algorithm for inverse kinematics problem in robotics. in Book of abstracts, International Conference of Experimental and Numerical Investigations and New Technologies CNN TECH 2021 46 Beograd : Inovacioni centar Masinskog fakulteta., 46-46. https://hdl.handle.net/21.15107/rcub_machinery_4089
Zivković NL, Vidaković J, Lazarević M. Hybrid pso-newton-raphson algorithm for inverse kinematics problem in robotics. in Book of abstracts, International Conference of Experimental and Numerical Investigations and New Technologies CNN TECH 2021 46. 2021;:46-46. https://hdl.handle.net/21.15107/rcub_machinery_4089 .
Zivković, Nikola Lj., Vidaković, Jelena, Lazarević, Mihailo, "Hybrid pso-newton-raphson algorithm for inverse kinematics problem in robotics" in Book of abstracts, International Conference of Experimental and Numerical Investigations and New Technologies CNN TECH 2021 46 (2021):46-46, https://hdl.handle.net/21.15107/rcub_machinery_4089 .