Task of an Energy Management Strategy within a vehicle is the optimization of its energy demand. In the case of autonomous vehicles, this includes the optimization of the planned trajectory as well as the power distribution within the vehicle’s powertrain components. For example, the energy demand rises sharply during highly dynamic driving maneuvers. In contrast, the time required to reach one’s destination gets reduced. For the optimization of the conflicting objectives, additional technical boundary conditions derived from the permissible states of the vehicle components need to be considered.

Aim of the project is the development of an optimization algorithm operating in real-time, calculating the vehicle’s Energy Management Strategy. The calculations base on objective functions that convert the vehicle signals into optimization parameters. The user specifies his preferences for different weighting factors of multiple objective functions. By this, it will be possible to use the same algorithm both in road relevant scenarios as well as on the racetrack. At the same time, the powertrain components will not leave their permissible operating ranges.

In a first step, suitable control parameters as well as objective variables, offering great potential for the optimization of the energy demand will be identified. These will then be implemented in suitable algorithms to deduce the Energy Management Strategy. Conventional algorithms will be compared to methods of Machine Learning.

The evaluation of the developed algorithms takes place within the framework of Roborace. The races of the autonomous Roborace series are held on regular Formula E courses.