Neural Network Based Approach to Positioning Task for the End-Effector of a Four-Joint Manipulator

Смирнов, Петр; Mikhalchenko, Daniil; Malov, Dmitrii

doi:10.1109/rusautocon.2018.8501688

Cited by 1 publication

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neural networks (NNs) are commonly used to solve the IK problem due to the abilities of modeling nonlinear relationships [3]. In many NN-based solutions, the IK function is modeled by a single fullyconnected feedforward neural network, the multi-layered perceptron (MLP), that directly takes the Cartesian coordinate of the target point as input and the joint angles as output [3,4,5,6,7]. However, when the degree-of-freedom (DOF) of the robot arm is high, the problem becomes complicated.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Joint Dependencies for Data-driven Inverse Kinematics with Neural Networks for High-DOF Robot Arms

Tsai¹,

King²,

Ho³

EPiC Series in Computing

View full text Add to dashboard Cite

Solving inverse kinematics (IK) has been an important problem in the field of robotics. In recent years, the solutions based on neural networks (NNs) are popular to handle the non-linearity of IK. However, the complexity of IK grows rapidly as the degree-of-freedom (DOF) of the robot arms increases. To address this problem, we exploit the dependencies among the joints of the robot arms, based on the observation that the movements of certain joints of a robot arm will affect the movements of other joints. We investigate the idea under a data-driven setting, i.e., the NN models are trained based on supervised learning through a given trajectory dataset. Several NN architectures are examined to exploit the joint dependencies of robot arms. A greedy algorithm is then presented to find a proper sequence of applying the joints to decrease the distance error. The experimental results on a 7-DOF robot arm show that the NN models using joint dependency can achieve the same accuracy as the single-MLP model but use fewer parameters.

show abstract