Motion control strategy for robotic arm using deep cascaded feature-enhancement Bayesian broad learning system with...

Area of Science:

• Robotics
• Control Systems Engineering
• Artificial Intelligence

Background:

• Existing intelligent control strategies for robotic arms using broad learning systems often lack accuracy and do not consider joint motion limitations.
• These limitations can negatively impact the overall control performance and safety of robotic systems.

Purpose of the Study:

• To propose an advanced robotic arm motion control strategy that improves accuracy and accounts for physical joint motion constraints.
• To enhance the stability and reliability of robotic arm control systems.

Main Methods:

• Development of a Deep Cascaded Feature-Enhanced Bayesian Broad Learning System (DCBBLS) to simplify modeling and boost control accuracy.
• Integration of a motion constraint mechanism to prevent robotic arm movements from exceeding physical limits.
• Application of Lyapunov theory to ensure the stability of the control strategy network parameters.

Main Results:

• The proposed MC-DCBLS strategy demonstrated significant improvements in robotic arm motion control accuracy.
• Position tracking root mean square error (RMSE) was reduced to 0.038 rad.
• This represents a 61.26% reduction in error compared to existing control techniques.

Conclusions:

• The MC-DCBLS strategy effectively addresses the accuracy and motion limitation challenges in robotic arm control.
• The method ensures stable and precise robotic arm movements within physical boundaries.
• Validated through simulations and experiments, the strategy offers a substantial advancement in intelligent robotic control.