Road transportation is proved to be one of the main contributor to pollutant and global greenhouse gas emissions. This, together with the rising of fuel price, is striving the automotive sector research towards innovative solutions. Promising solutions fuel cell vehicles, which generally make use of polymer electrolyte membrane fuel cells with the possibility of further reducing pollutant emissions, giving a satisfactory range without the need of an internal combustion engine. Nonetheless, even being a relatively mature technology, there are still some disadvantages related to the use of fuel cells for vehicles, such as high costs, low power density, and lack of hydrogen infrastructures. The latter issue could be solved by using an on-board fuel processor for hydrogen production. This paper describes the energy management controller design of a mid-sized vehicle driven by a fuel cell/battery plug-in hybrid powertrain, where an experimentally validated high temperature polymer electrolyte membrane fuel cell model is used. The power management strategy is derived by the application of the Pontryagin's Minimum Principle, where the control parameter is adapted by using feedback information on the state of charge and total trip length forecast as a function of a moving average of past information about the driving cycle speed. The strategy we propose aims at achieving a real time sub-optimal solution of the control problem, which is cast into the minimization of the consumed fuel. The vehicle is also equipped by an autothermal reformer and, in order to minimize the hydrogen buffer size, the control algorithm is subject to constraints on the maximum hydrogen buffer level. The effectiveness of the adaptive control strategy is analyzed when feeding the autothermal reformer with different fuels. The different solutions are compared both in terms of fuel consumption, control strategy ability to adapt to different driving conditions and overall system efficiency.