Motion Adaptation Based on Learning the Manifold of Task and Dynamic Movement Primitive Parameters. Issue 7 (18th July 2021)

• Record Type: Journal Article
• Authors: Cohen, Yosef; Bar-Shira, Or; Berman, Sigal
• Is Part Of: Robotica. Volume 39:Issue 7(2021)
• Page Start: 1299
• Page End: 1315
• Publication Date: 2021-07-18
• Subjects: Dynamic movement primitives, -- Kernel estimation, -- Deep Neural networks, -- Motion planning, -- Learning; Robots -- Periodicals; 629.89205
• DOI: 10.1017/S0263574720001186
• Languages: English
• ISSNs: 0263-5747

Abstract

SUMMARY: 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.