Estimating device, estimating method, and estimating program

An estimating method in which a computer:

• acquires information from a detecting section that detects electrical characteristics between a plurality of predetermined detection points at a flexible material that is electrically conductive and has electrical characteristics that vary in accordance with a magnitude of an applied stimulus and that is at an assisting member that has the flexible material and is provided at a transporting section that transports a transported object;
• and
• inputs time-series electrical characteristics detected by the detecting section to a learning model that is trained by using, as learning data, time-series electrical characteristics at times when a stimulus was applied to the flexible material, and placed state information expressing a placed state of the transported object with respect to the assisting member that applies a stimulus to the flexible material, or contact state information expressing a contact state with an external object that applies deformation to the flexible material, or behavior state information that expresses a behavior state of the transported object with respect to the assisting member that applies a stimulus to the flexible material, such that the time-series electrical characteristics are inputs of the learning model and the learning model outputs the placed state information or the contact state information or the behavior state information, and the computer estimates placed state information expressing a placed state corresponding to inputted time-series electrical characteristics, or contact state information expressing a contact state corresponding to inputted time-series electrical characteristics, or behavior state information expressing a behavior state corresponding to inputted time-series electrical characteristics.

A non-transitory computer-readable medium storing an estimating program for causing a computer to execute processing of:

• acquiring information from a detecting section that detects electrical characteristics between a plurality of predetermined detection points at a flexible material that is electrically conductive and has electrical characteristics that vary in accordance with a magnitude of an applied stimulus and that is at an assisting member that has the flexible material and is provided at a transporting section that transports a transported object;
• and inputting time-series electrical characteristics detected by the detecting section to a learning model that is trained by using, as learning data, time-series electrical characteristics at times when a stimulus was applied to the flexible material, and placed state information expressing a placed state of the transported object with respect to the assisting member that applies a stimulus to the flexible material, or contact state information expressing a contact state with an external object that applies deformation to the flexible material, or behavior state information that expresses a behavior state of the transported object with respect to the assisting member that applies a stimulus to the flexible material, such that the time-series electrical characteristics are inputs of the learning model and the learning model outputs the placed state information or the contact state information or the behavior state information, and the computer estimates placed state information expressing a placed state corresponding to inputted time-series electrical characteristics, or contact state information expressing a contact state corresponding to inputted time-series electrical characteristics, or behavior state information expressing a behavior state corresponding to inputted time-series electrical characteristics.