Scholarlink

Learning from demonstrations (LfD) provides a low-cost and effective way for robot programming and has drawn a lot of research attention in recent decades (Ravichandar et al. in Annu Rev Control Rob Autonom Syst 3:297–330, 2020 [1]). Dynamic movement primitives (DMP), proposed by Schaal (Adaptive motion of animals and machines. Springer, Tokyo, 2006 [2]), is a practical branch of LfD and first enables an artificial agent to act a complex human-like action in a versatile and creative manner (Saveriano in Int J Rob Res 42(13):1133–1184, 2021 [3]). As is mentioned in Saveriano (Int J Rob Res 42(13):1133–1184, 2021 [3]), DMP is full of advantages, such as simple and elegant formulation, convergence to a given target, flexibility for complex behaviours, and the capability of reacting to some external perturbations.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Incremental Motor Skill Learning and Generalization from Human Dynamic Reactions Based on Dynamic Movement Primitive and Fuzzy Logic System

  • 章节

  • 发表日期：

    2025年

查看全文
  • Chenguang Yang,
  • Zhenyu Lu,
  • Ning Wang

摘要

Learning from demonstrations (LfD) provides a low-cost and effective way for robot programming and has drawn a lot of research attention in recent decades (Ravichandar et al. in Annu Rev Control Rob Autonom Syst 3:297–330, 2020 [1]). Dynamic movement primitives (DMP), proposed by Schaal (Adaptive motion of animals and machines. Springer, Tokyo, 2006 [2]), is a practical branch of LfD and first enables an artificial agent to act a complex human-like action in a versatile and creative manner (Saveriano in Int J Rob Res 42(13):1133–1184, 2021 [3]). As is mentioned in Saveriano (Int J Rob Res 42(13):1133–1184, 2021 [3]), DMP is full of advantages, such as simple and elegant formulation, convergence to a given target, flexibility for complex behaviours, and the capability of reacting to some external perturbations.