Drinking is an essential activity of daily living (ADL) that is frequently required for a healthy life. Disabled persons however need recurrent assistance from the caregivers to perform such ADL. The existing assistive robots that have been developed to assist in performing ADL require either manual or shared control. There is therefore need for completely autonomous systems that can deal with the existing system limitations. In this paper, a hybrid impedance control-based autonomous robotic system for natural-like drinking assistance for disabled persons is developed. The system comprises of a UR-10 manipulator and a Kinect RGB-D sensor for online detection of the face and mouth along with tracking head pose, cup region of interest recognition and detection of the drink level. A two-stage control strategy is employed; namely, a free-space control to convey an upright oriented cup of drink to the user’s mouth and in-contact compliant control to continuously reorient the cup. Online trajectory replanning is conducted in case of unintentional head and mouth pose changes. A hybrid impedance control is developed to tackle three cases of cup and user’s mouth contact; namely, permissible contact force, contact loss and exceeding the contact force threshold. Simulation results based on co-simulating the manipulator dynamics in ADAMS and MATLAB indicate high performance of the controller in terms of tracking the generated pose and desired force trajectories during the drinking task. The results also indicate that the proposed system can conduct the drinking assistance autonomously.