Method and apparatus for industrial robotic energy saving optimization using fly-by

A data processing system comprising:

• a processor;
• and
• an accessible memory, the data processing system particularly configured to:
• initialize a plurality of clone paths where a collision was detected and a stop condition, wherein a clone path is a clone of an initial path and the initial path comprises a source location, a plurality of intermediate locations, and a target location;
• until the stop condition occurs, determine a candidate path to store in a population by repeating:
• apply a plurality of mutations to a selected clone path;
• generate a graph with a plurality of zone permutation vertices for each of the plurality of intermediate locations of the selected clone path and a plurality of rating edges between each zone permutation vertex of consecutive locations, wherein each of the plurality of zone permutation vertices has a radius one increment larger than a previous zone permutation vertex;
• simulate robotic movement of the candidate path to determine values for the rating edges, wherein the value of the rating edges is based on an energy consumption and a cycle time;
• remove the candidate path when a collision is detected;
• calculate a breed rating for each of a plurality of candidate paths, wherein the breed rating comprises a summation of the rating edges for the candidate path;
• and
• store the candidate path possessing a lowest breed rating in the population;
• determine an optimal breed comprising the candidate path with an optimal rating, wherein the optimal rating is determined by the lowest breed rating in the population;
• and
• operate a robot using the optimal breed.

A non-transitory computer-readable medium encoded with executable instructions that, when executed, cause one or more data processing systems to:

• initialize a plurality of clone paths where a collision was detected and a stop condition, wherein a clone path is a clone of an initial path and the initial path comprises a source location, a plurality of intermediate locations, and a target location;
• until the stop condition occurs, determine a candidate path to store in a population by repeating:
• apply a plurality of mutations to a selected clone path;
• generate a graph with a plurality of zone permutation vertices for each of the plurality of intermediate locations of the selected clone path and a plurality of rating edges between each zone permutation vertex of consecutive locations, wherein each of the plurality of zone permutation vertices has a radius one increment larger than a previous zone permutation vertex;
• simulate robotic movement of the candidate path to determine values for the rating edges, wherein the value of the rating edges is based on an energy consumption and a cycle time;
• remove the candidate path when a collision is detected;
• calculate a breed rating for each of a plurality of candidate paths, wherein the breed rating comprises a summation of the rating edges for the candidate path;
• and
• store the candidate path possessing a lowest breed rating in the population;
• determine an optimal breed comprising the candidate path with an optimal rating, wherein the optimal rating is determined by the lowest breed rating in the population;
• and
• operate a robot using the optimal breed.