Methods, apparatuses, and systems for performing robotic surgery in an extended reality (XR) collaborative customizable virtual operating room are disclosed. The disclosed systems provide a virtual environment in which a surgical robot network receives medical images of a patient and creates a digital twin from a patient's medical images. The surgical robot network allows a first user to create a virtual environment to perform a surgical procedure, select workflow objects, and perform actions on the digital twin. The data of the workflow objects and actions in relation to the digital twin is stored. The first user invites a second user to join the virtual environment who may collaborate with the first user on the workflow objects and actions performed to adjust the workflow, workflow objects, and actions performed. The workflow, workflow objects, actions in relation to the digital twin are sent to a surgical robot.