We propose a new framework combining decision making and planning in the human-robot co-navigation scenario. This new framework, called HATEB-2, introduces different modalities of planning and shift between them based on the situation at hand. These transitions are controlled by the decision making loop present on top of the planning. We also present the improvements made to human prediction and estimation along with the modifications to a few social constraints from our previous work, that are included in HATEB-2. Finally, several experiments are performed in human-robot co-navigation scenarios and results are presented. One of the modalities of HATEB-2 is used in EU-funded MuMMER [1] project (http://mummer-project.eu/).