Method, system, and storage medium for selecting grasp posture of dual-arm robot

A system for selecting a grasp posture of a dual-arm robot, comprising:

• a parameter setting module, configured to:
• determine a value range of a fitness function and an iteration quantity threshold with a goal of minimizing the posture variation at the end effectors of dual arms, design the fitness function based on a position relationship between the dual arms and the to-be-grasped rod member and motion laws of the dual arms, and set initial crossover and mutation ratios;
• a generation module, configured to take initial postures of the dual arms and the position of the target to-be-grasped rod member as constraints for generating an initial population, and generate an initial population representing a grasping position;
• the above specific content of taking the initial posture of the dual arms and the position of the target to-be-grasped rod member as constraints for generating an initial population are as follows:
• the target grasping points are generated on the axis of the target object to be grasped, and the initial population of each gene group contains two points representing the dual-arm target positions distributed on both sides of the object's centroid;
• a calculation module, configured to calculate fitness of each group of genes in the population based on the fitness function designed by the parameter setting module;
• a determining module, configured to perform two-step determining, where the first step is to determine whether the fitness calculated by the calculation module for each group of genes in the population is within the value range set by the parameter setting module for the fitness function, if it does, obtain an optimal target corresponding to the dual arms, or otherwise, then perform to the second step, checking if the iteration count reaches the threshold value set in the parameter setting module, if it does, the optimal targets for the dual arms are obtained, otherwise, it execute the crossover and mutation module;
• a crossover and mutation module, configured to obtain a new-generation population gene through crossover and mutation operations;
• a gene retention module, configured to:
• for a population gene that is not processed by the crossover and mutation module, dynamically select a gene retention strategy based on an iteration depth of the population gene in the quantity of iterations, a fitness value, the grasping position, and postures at the tail ends of the dual arms, to retain the gene;
• and
• an update module, configured to update, based on the new-generation population gene obtained by the crossover and mutation module and the gene retained by the gene retention module, a population gene representing the grasping position, and return to the calculation module until the optimal target corresponding to the dual arms is obtained.