RNN and bidirectional-RNN feedforward compensators, trained on measured Baxter motion, reduce trajectory tracking error by roughly 30 to 50 percent versus feedback-only control.
Feedback- error-learning neural network for trajectory control of a robotic ma- nipulator,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neural-Learning Trajectory Tracking Control of Flexible-Joint Robot Manipulators with Unknown Dynamics
RNN and bidirectional-RNN feedforward compensators, trained on measured Baxter motion, reduce trajectory tracking error by roughly 30 to 50 percent versus feedback-only control.