Table 5 Deviation errors on circular and square paths in Q1.

From: Path-based evaluation of deep learning models for solving inverse kinematics in a revolute-prismatic robot

Model

Path shape

Deviation error (mm)

DFNN with K-fold CV (single o/p)

Square

0.289

DFNN with K-fold CV (dual o/p)

0.772

DFNN without CV

1.301

LSTM

1.083

GRU

0.957

DFNN with K-fold CV (single o/p)

Circle

0.312

DFNN with K-fold CV (dual o/p)

1.048

DFNN without CV

1.785

LSTM

1.027

GRU

0.677

Back to article page