Techniques, machine learning, and mechanisms for enabling supply of energy to devices

A non-transitory computer-readable medium storing instructions executable by at least one hardware processor to perform operations for automatically enabling supply of energy to a machine using a movable member comprising a camera and an energy supply mechanism, the operations comprising:

• positioning the movable member to a first orientation angle to capture image data using the camera;
• accessing a trained machine learning model associated with the machine;
• identifying, based on the trained machine learning model and the captured image data, an energy input location of the machine, wherein the trained machine learning model is configured to segment types of objects represented in the captured image data, and wherein identifying the energy input location includes determining:
• a position of the energy input location relative to three perpendicular axes, and
• an orientation of the energy input location relative to each of the three perpendicular axes;
• based on the determined position and orientation of the energy input location, positioning the movable member to a second orientation angle different from the first orientation angle;
• moving the energy supply mechanism into a position according to the energy input location, wherein the positioning of the movable member to the second orientation angle and moving the energy supply mechanism into the position are based on the image data captured by the camera while the movable member is positioned in the first orientation angle without requiring additional image data captured by the camera after the movable member is moved from the first orientation angle;
• and
• enabling supply of energy via the energy supply mechanism to the machine at the energy input location.