Robot work system and method of controlling robot work system

A robot work system in which a robot performs work on a work target transported by a transport machine, comprising:

• an information processing apparatus that includes a processor and a storage device,
• wherein the information processing apparatus comprises
• a recognition processing unit that obtains a plurality of combinations of a position of a work target candidate and a transport machine optimum control parameter which is a control parameter of the transport machine that maximizes performance of the work on a work target when the work target candidate is set as the work target, based on a captured image obtained by capturing an area including a plurality of the work target candidates transported by the transport machine,
• a work target determination unit that determines a work target from among the work target candidates based on the combinations,
• a transport machine control unit that controls the transport machine based on the transport machine optimum control parameter of the determined work target, and
• a robot control plan generation unit that generates a control plan of the robot based on a position of the determined work target and the transport machine optimum control parameter of the work target, and
• the recognition processing unit, the work target determination unit, the transport machine control unit, and the robot control plan generation unit are realized by reading out and executing a program stored in the storage device by the processor;
• wherein the recognition processing unit is realized by a learning model of machine learning obtained by learning of learning data with the captured image which is acquired by capturing the area including the plurality of work target candidates, as an input and a combination of the position of the work target candidate and a performance when a robot optimum control parameter which is a control parameter of the robot that maximizes the performance is fixed as an out but:
• wherein the recognition processing unit is realized by a plurality of the learning models prepared for each discrete value of the control parameter of the robot.

A method of controlling a robot work system in which a robot performs work on a work target transported by a transport machine, comprising:

• by an information processing apparatus including a processor and a storage device,
• obtaining a plurality of combinations of a position of a work target candidate and a transport machine optimum control parameter that is a control parameter of the transport machine that maximizes performance of the work on a work target when the work target candidate is set as the work target, based on a captured image obtained by capturing an area including a plurality of the work target candidates transported by the transport machine;
• determining the work target from among the work target candidates based on the combinations;
• controlling the transport machine based on the transport machine optimum parameter of the determined work target;
• and
• generating a control plan of the robot based on a position of the determined work target and the transport machine optimum control parameter of the work target;
• wherein the steps of the method are realized by a learning model generated by machine learning of learning data with the captured image which is acquired by capturing the area including the plurality of work target candidates, as an input and a combination of the position of the work target candidate and the performance when the control parameter of the transport machine is fixed, as an output;
• and
• wherein a plurality of the learning models are prepared for each discrete value of the control parameter of the transport machine.