This paper deals with trajectory generation for redundant manipulators
with structured intelligence. Recently, behavior engineering for robo
tic systems has been discussed as a new technological discipline. The
intelligence of a robot depends on the structure of hardware and softw
are for processing information, i.e. the structure determines the pote
ntiality of intelligence. This paper proposes a robotic system with st
ructured intelligent based on subsumption-like architecture. Based on
perceptual information, a robot with structured intelligence makes dec
isions and takes action from four levels in parallel. In addition, the
robot generates its motion through interaction with the environment a
nd, at the same time, gradually acquires its skill based on the genera
ted motion. To acquire skill and motion, the robot requires internal a
nd external evaluations at least. This paper applies a virus-evolution
ary genetic algorithm to trajectory planning for redundant manipulator
s with structured intelligence. Furthermore, we discuss its effectiven
ess through computer simulation results.