This paper presents a new human-robot
interaction control approach for industrial robot oim.
With fiame-based knowledge representation, a human-
robot system as well (IS its interaction controi process is
modeled and defined in the Sofiare Plarform of Agents
and Knowledge Management (SPAK). By means of this
s0fh.a.e platform, human-robot interaction control for
industrial robot arm is implemented. In this paper, on
actual system comprised of human, humanoid robot
(Robovie) ond industrial robot arm (MELFA) is
constructed and the experimental results demonsirate its
effectiveness.