Gesteme-free context-aware adaptation of robot behavior in human–robot cooperation
作者：
Highlights：
• We classify user's actions during robotic cooperation using a gesteme-free algorithm.
• We accordingly adapt the manipulator's dynamics with sigmoidal-shaped functions.
• We tested the system over 12 naive users during targeting tasks on soft tissue.
• The algorithm provides 80% accuracy after observing 450 ms of signal.
• The proposed dynamics adaptation does not lead to unstable behavior (high smoothness).
摘要
Highlights•We classify user's actions during robotic cooperation using a gesteme-free algorithm.•We accordingly adapt the manipulator's dynamics with sigmoidal-shaped functions.•We tested the system over 12 naive users during targeting tasks on soft tissue.•The algorithm provides 80% accuracy after observing 450 ms of signal.•The proposed dynamics adaptation does not lead to unstable behavior (high smoothness).
论文关键词：Activity recognition,Cooperative robotics,Context-awareness
论文评审过程：Received 19 March 2016, Revised 22 October 2016, Accepted 25 October 2016, Available online 28 November 2016, Version of Record 1 December 2016.
论文官网地址：https://doi.org/10.1016/j.artmed.2016.10.001
