The invention discloses an
inverse kinematics solving method and device for a
service robot in a smart space. The method includes the following steps that: the
forward kinematics model of the
robot isestablished by using a D-H parameter method; real number coding is performed on the joint variables of the
robot; an adaptive function is constructed with difference between a current
pose and a target
pose adopted as an optimization objective; and a
genetic algorithm is used to perform optimization solution on the joint variables, so that the optimal solution of the
inverse kinematics problem isobtained. The method of the invention does not need to be limited to
robot configurations, and a plurality of populations are introduced, so that
parallel optimization search can be realized, and therefore, the method can cope with the increase of the degree of freedom of the robot; the real number coding is adopted for the individuals, and mapping errors occurring during continuous function
discretization when binary coding is adopted can be avoided; and on the basis of the real number coding,
crossover operation adopts a linear
crossover mode,
mutation operation adopts a
random mutation mode, and adaptive
crossover and
mutation probabilities are introduced, and therefore, a better solution can be effectively protected in the later stage of evolution, and convergence speed and precisioncan be guaranteed.