Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters

Yosef Cohen, Or Bar-Shira, Sigal Berman

Research output: Contribution to journalArticlepeer-review

8 Scopus citations


Dynamic movement primitives (DMP) are motion building blocks suitable for real-world tasks. We suggest a methodology for learning the manifold of task and DMP parameters, which facilitates runtime adaptation to changes in task requirements while ensuring predictable and robust performance. For efficient learning, the parameter space is analyzed using principal component analysis and locally linear embedding. Two manifold learning methods: kernel estimation and deep neural networks, are investigated for a ball throwing task in simulation and in a physical environment. Low runtime estimation errors are obtained for both learning methods, with an advantage to kernel estimation when data sets are small.

Original languageEnglish
Pages (from-to)1299-1315
Number of pages17
Issue number7
StatePublished - 1 Jul 2021


  • Deep Neural networks
  • Dynamic movement primitives
  • Kernel estimation
  • Learning
  • Motion planning

ASJC Scopus subject areas

  • Software
  • Mechanical Engineering
  • Control and Optimization
  • Artificial Intelligence
  • General Mathematics
  • Rehabilitation
  • Control and Systems Engineering
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Computational Mechanics
  • Modeling and Simulation


Dive into the research topics of 'Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters'. Together they form a unique fingerprint.

Cite this