Robot dynamics identification via neural network

Dyda, Alexander A.; Оськин, Д. А.; Artemiev, Andrey V.

doi:10.1109/idaacs.2015.7341437

Cited by 4 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other approaches that are implemented for AUV are the use of feedback navigation systems [23], or a recurrent network to control the tethered UV [24]. However, they are based either on the deterministic data from a feedback sensor system or on data of the deterministic model [21,22], which is represented in ICS [24]. This is especially true for AUV, which lack wireless navigation systems and which do not have external factors for determining their spatial position [23].…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

“…Thus, the ease of determining the angular position and coordinates and the complexity of recording the forces and moments are typical of ICS [23]. And vice versa, the connected coordinate system is characterized by the ease of determining the forces and moments and the complexity in determining the angular position and coordinates [24]. The latter makes the main unresolved problem the construction of model that would take into account the impact of angular position of AUV in ICS and would enable determining its kinematical parameters, selecting it by several alternatives [25].…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

“…For example, applying for ground-based mobile complexes [21], equipped with manipulators of developed sensor systems [22], the principles of fuzzy logic partially eliminates the drawbacks in the models of dynamics. Other approaches that are implemented for AUV are the use of feedback navigation systems [23], or a recurrent network to control the tethered UV [24]. However, they are based either on the deterministic data from a feedback sensor system or on data of the deterministic model [21,22], which is represented in ICS [24].…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

See 2 more Smart Citations

Recurrent transformation of the dynamics model for autonomous underwater vehicle in the inertial coordinate system

Trunov

2017

EEJET

View full text Add to dashboard Cite

Система нелінійних диференціальних рівнянь руху автономного підводного апарату (АПА) з маніпуля-тором на борту у інерціальній системі координат (ІСК) трансформована до рекурентної послідовності. Аналітичні вирази лінійних та кутових швидкостей, кутових положень та координат АПА у ІСК отрима-ні для повної кінематичної матриці. Представлено вирази похибки кутових положень, що виникають внаслідок спрощень кінематичної матриці Ключові слова: автономний підводний апарат, інерціальна система координат, рекурентна послі-довність, кінематична матриця Система нелинейных дифференциальных урав-нений движения автономного подводного аппарата (АПА) с манипулятором на борту в инерциальной системе координат (ИСК) преобразована к рекур-рентной последовательности. Аналитические выра-жения линейных и угловых скоростей, угловых поло-жений и координат АПА в ИСК получены для полной кинематической матрицы. Представлены выраже-ния ошибки угловых положений, которые возникают вследствие упрощений кинематической матрицы Ключевые слова: автономный подводный аппа-рат, инерциальная система координат, рекуррент-ная последовность, кинематическая матрица UDC

show abstract

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Section: Literature Review and Problem Statementmentioning

confidence: 99%

Section: Literature Review and Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Recurrent transformation of the dynamics model for autonomous underwater vehicle in the inertial coordinate system

Trunov

2017

EEJET

View full text Add to dashboard Cite

show abstract

“…C Li et al [9] present a novel dynamic modeling method by using a recurrent neural network (RNN) with an incomplete state system variables observation. The RNN family are also used for robotic manipulator model learning tasks [10] and approximating robot dynamical models [11,12]. However, studies with many kinds of complex characteristics combined are limited.…”

Section: Introductionmentioning

confidence: 99%

A Systematic Error Compensation Strategy Based on an Optimized Recurrent Neural Network for Collaborative Robot Dynamics

Zhang

Hou

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

Robot dynamics and its parameter identification are of great significance to the realization of optimal control and human–machine interaction. The objective of this research is to address the shortcomings of establishing and identifying the self-developed six-degree-of-freedom (6-DoF) collaborative robot dynamics, which leads to a large error in the predicted torque of the proposed robot. A long short-term memory (LSTM) in an optimized recurrent neural network (RNN) is proposed to compensate the dynamic model of the proposed 6-DoF collaborative robot based on the consideration of gravity, Coriolis force, inertial force, and friction force. The analysis and experimental findings provide promising results. The compensated collaborative robot dynamic model based on LSTM in an optimized RNN displays a good prediction on the actual torque, and the root-mean-square (RMS) error between predicted and actual torques are reduced by 61.8% to 78.9% compared to the traditional dynamic model. Results of the experimental applications demonstrate the validity of the proposed systematic error compensation strategy.

show abstract