Table 13 Deviation errors on circular and square paths in Q3.

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

0.508

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

0.637

DFNN without CV

0.890

LSTM

0.521

GRU

1.295

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

Circle

0.438

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

0.756

DFNN without CV

0.739

LSTM

0.590

GRU

1.269

Back to article page