Sign in Subscribe
Robotics industry

Advances in Robotics: Stable Skill Learning and Adaptive Control Strategies

Strategic Insights

— 1 min read

Researchers at the Guangdong Academy of Science have made a breakthrough in robotics by developing a stable skill learning and adaptive variable impedance control framework for machining heterogeneous material components. The framework, which has been validated through two experiments, enhances machining accuracy and reduces impact force compared to traditional controllers. The study, supported by the National Natural Science Foundation of China and the National Key Research & Development Program of China, has been published in the Journal of Manufacturing Processes.

Key Takeaways:

  • The researchers developed a human demonstration-based robotic machining framework for heterogeneous material components (HMCs) that adapts to external perturbations and handles varying material dynamics.
  • The framework, which consists of a stable, nonlinear dynamical system and a variable impedance controller, improves machining accuracy and reduces impact force compared to traditional controllers.
  • In the 'paper-plastic foam-wood' laminated component drilling task, the average diameter error was reduced by 54% compared to traditional controllers, with an average diameter error of 0.676 mm.
  • In the polishing experiment with 'wood-iron' transverse splicing components, the maximum impact force was reduced to 3.384N, with a cross-material maximum impact force of 3.547N.
  • The study demonstrates the effectiveness of the stable skill learning and adaptive variable impedance control framework in improving the processing of HMCs.
  • The research has been peer-reviewed and published in the Journal of Manufacturing Processes.

Statistics:

  • Average diameter error in the 'paper-plastic foam-wood' laminated component drilling task: 0.676 mm
  • Reduction in average diameter error compared to traditional controllers: 54%
  • Maximum impact force in the polishing experiment with 'wood-iron' transverse splicing components: 3.384N
  • Cross-material maximum impact force: 3.547N
  • Number of experiments tested: 2
  • Number of researchers involved in the study: 6

Sources:

  • Learning Stability-guaranteed Skill and Adaptive Control Strategies From Demonstrations for Heterogeneous Component Robotic Machining. Journal of Manufacturing Processes, 2025;151:506-520.
  • Guangdong Academy of Science, Inst Intelligent Mfg, Guangzhou 510070, Guangdong, People's Republic of China.
  • Elsevier Sci Ltd, 125 London Wall, London, England. (www.elsevier.com; www.journals.elsevier.com/journal-of-manufacturing-processes/)
  • National Natural Science Foundation of China (NSFC)
  • National Key Research & Development Program of China
  • Guangdong Basic and Applied Basic Research Foundation
  • GDAS' Project of Science and Technology Development

Read more