Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Progressive learning and its application to robot impedance learning.

B H Yang1, H Asada

  • 1Dept. of Mech. Eng., MIT, Cambridge, MA.

IEEE Transactions on Neural Networks
|January 1, 1996
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Evidence for the Collective Nature of Radial Flow in Pb+Pb Collisions with the ATLAS Detector.

Physical review letters·2026
Same author

Evidence for the Dimuon Decay of the Higgs Boson in pp Collisions with the ATLAS Detector.

Physical review letters·2025
Same author

Evidence for Longitudinally Polarized W Bosons in the Electroweak Production of Same-Sign W Boson Pairs in Association with Two Jets in pp Collisions at sqrt[s]=13  TeV with the ATLAS Detector.

Physical review letters·2025
Same author

[Prognosis and risk factors of different recurrence and metastasis patterns following pancreatectomy].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2025
Same author

Observation of tt[over ¯] Production in Pb+Pb Collisions at sqrt[s_{NN}]=5.02  TeV with the ATLAS Detector.

Physical review letters·2025
Same author

Search for Dark Matter Produced in Association with a Dark Higgs Boson in the bb[over ¯] Final State Using pp Collisions at sqrt[s]=13  TeV with the ATLAS Detector.

Physical review letters·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces progressive learning, a novel excitation scheduling technique for robotic control. It stabilizes learning by gradually increasing system excitation, enabling robots to master complex tasks like fast assembly.

Area of Science:

  • Robotics
  • Control Theory
  • Machine Learning

Background:

  • Traditional adaptive and learning control methods often face instability issues due to system input variations.
  • Robotic assembly requires controllers that can adapt to both slow and fast movements, posing a significant challenge for existing techniques.

Purpose of the Study:

  • To develop and apply a new excitation scheduling technique, termed progressive learning, to address instability in learning control systems.
  • To enhance impedance learning for fast robotic assembly by enabling stable adaptation to dynamic parameters.

Main Methods:

  • The study employs a progressive learning approach, which involves a scheduled increase in system excitation levels.
  • Impedance learning is formulated as a model-based, gradient-following reinforcement learning problem.

Related Experiment Videos

  • The technique prioritizes learning quasistatic parameters with slow inputs before progressing to dynamic parameters with faster inputs.

    • Main Results:

    • Progressive learning successfully avoids instability by progressively increasing system excitation, allowing for stable learning of control parameters.
    • The method enables robots to learn impedance control parameters (stiffness, damping, inertia) effectively, starting from slow motions and progressing to fast ones.
    • Excessive parameter changes are suppressed, stabilizing the learning process and allowing for effective learning within expanding parameter spaces.

    Conclusions:

    • The developed progressive learning technique offers a stable and effective method for impedance learning in robotic assembly.
    • By gradually increasing motion speed commands, robots can learn internal models and control parameters more efficiently.
    • This approach provides a robust solution for complex robotic tasks requiring adaptation to varying dynamics.