Adaptive Control Strategies for Manipulator Visual Servoing: Sliding Mode and Neural Networks Integration

EasyChair Preprint 13188

Abstract

This research paper investigates adaptive control strategies tailored for manipulator visual servoing, a critical aspect of robotic systems where precise control over manipulator motion is required for tasks involving visual feedback. Visual servoing presents unique challenges due to uncertainties in the environment, camera calibration, and varying illumination conditions. Traditional control methods often struggle to maintain performance under these conditions, necessitating the development of adaptive control strategies. This paper proposes novel adaptive control techniques that enable manipulators to adapt their control parameters in real-time based on visual feedback, thus improving robustness and performance in dynamic environments. The effectiveness of the proposed strategies is validated through simulations and experimental results, demonstrating their potential for enhancing the efficiency and reliability of manipulator visual servoing systems.

Keyphrases: Rigid-Deformable Objects, adaptive control, manipulation, manipulator, visual servoing

@booklet{EasyChair:13188,
  author    = {Wahaj Ahmed and Derick Burns},
  title     = {Adaptive Control Strategies for Manipulator Visual Servoing: Sliding Mode and Neural Networks Integration},
  howpublished = {EasyChair Preprint 13188},
  year      = {EasyChair, 2024}}