In vitro simulation of three-dimensional (3D) shoulder motion using in vivo kinematics obtained from human subjects allows investigation of clinical conditions in the context of physiologically relevant biomechanics. Herein, we present a framework for laboratory simulation of subject-specific kinematics that combines individual 3D scapular and humeral control in cadavers. The objectives were to: (1) robotically simulate seven healthy subject-specific 3D scapulothoracic and glenohumeral kinematic trajectories in six cadavers, (2) characterize system performance using kinematic orientation accuracy and repeatability, and muscle force repeatability metrics, and (3) analyze effects of input kinematics and cadaver specimen variability. Using an industrial robot to orient the scapula range of motion (ROM), errors with repeatability of ±0.1 mm and <0.5 deg were achieved. Using a custom robot and a trajectory prediction algorithm to orient the humerus relative to the scapula, orientation accuracy for glenohumeral elevation, plane of elevation, and axial rotation of <3 deg mean absolute error (MAE) was achieved. Kinematic accuracy was not affected by varying input kinematics or cadaver specimens. Muscle forces over five repeated setups showed variability typically <33% relative to the overall simulations. Varying cadaver specimens and subject-specific human motions showed effects on muscle forces, illustrating that the system was capable of differentiating changes in forces due to input conditions. The anterior and middle deltoid, specifically, showed notable variations in patterns across the ROM that were affected by subject-specific motion. This machine provides a platform for future laboratory studies to investigate shoulder biomechanics and consider the impacts of variable input kinematics from populations of interest, as they can significantly impact study outputs and resultant conclusions.