Machines with feeling analogues

A method for operating a system implementing artificial analogues of feelings in machines, the system comprising a housing formed of material that is (i) soft, (ii) flexible, (iii) stretchable, (iv) deformable, or (v) any combination of (i)-(iv), the method comprising:

• receiving (i) data associated with one or more physical properties of the housing from a first sensor disposed on a surface of the housing, (ii) data associated with an environment external to the housing from a second sensor positioned spaced apart from the housing, and (iii) data associated with a status of at least one of the first and second sensors from a third sensor disposed at least partially inside the housing;
• storing the received data in one or more memory devices of the system;
• implementing one or more neural networks by one or more processing devices and the one or more memory devices, the one or more neural networks having one or more inputs and one or more outputs;
• determining a value of the one or more outputs of the one or more neural networks based at least in part on the received data;
• determining a homeostasis level of the system based at least in part on the determined value of the one or more outputs by determining a physical status of the housing and determining an impact the environment external to the housing has on the physical status of the housing, the homeostasis level of the system being based at least on (i) the data associated with the one or more physical properties of the housing received from the first sensor and (ii) the data associated with the environment external to the housing received from the second sensor;
• and
• modifying an execution of a task based on the determined homeostasis level to correct the homeostasis level of the system, wherein modifying the execution of the task includes operating one or more actuators of the system in order to cause the system to execute the task,
• wherein the inputs to the one or more neural networks include (i) the data associated with the one or more physical properties of the housing and (ii) the data associated with the environment external to the housing, and
• wherein the outputs to the one or more neural networks are based at least on (i) the data associated with the one or more physical properties of the housing and (ii) the data associated with the environment external to the housing.