A system for tracking a physical object comprises a robotic device, an instrument attachable to said robotic device, the instrument being configured to treat tissue, a vision device attached to one of said robotic device or said instrument such that said vision device is movable with said robotic device, said vision device configured to generate vision data sets, wherein said vision data sets are captured from multiple perspectives of the physical object enabled by said vision device being moved in a plurality of degrees of freedom when moving said robotic device, and at least one processor being in communication with said vision device, the at least one processor being configured to associate a virtual object with the physical object based on one or more features of the physical object identifiable in said vision data sets, wherein the virtual object at least partially defines a virtual boundary defining a constraint on movement of the robotic device relative to the physical object.