Xingrui Li
Environmental information, uncertainty conditions, radial basis function, neural network, robotic arm, impedance control
Because of its many benefits, including great production efficiency and high precision machining, mechanical arms are utilised extensively in many different sectors. However, the deployment of compliant control faces obstacles as production activities become more complicated. To address the aforementioned problems, the study first models the pertinent models and the robotic arm’s impedance models. It next suggests a radial basis function neural network (RBFNN)-based impedance control technique for the robotic arm to enhance the control’s transient performance. Lastly, the challenge of determining reference trajectories under unknown environmental information situations is addressed by an impedance control approach for robotic arms that is based on reference trajectory generation and environment estimating methods. According to the study findings, the contact force effect is reduced to 7.98N under the same conditions when using the RBFNN impedance control approach for robotic arms. The reference trajectory value obtained when the control system is stable is 0.0502 m in the impedance control method of a robotic arm based on reference trajectory generation and environment estimation algorithms; the maximum overshoot of the actual contact force at the end of the robotic arm is 2.1 N. The contact force stays constant after 2.53 s, and the associated error also stabilises at 0. In conclusion, the suggested approach has successfully raised robotic arms’ compliance control performance in the face of erratic environmental information.
Important Links:
Go Back
