Energy management strategy is essential for HEV’s to achieve an optimum of energy consumption. With predictive energy management, taking future vehicle speed predicted from ADAS map information, in-vehicle navigation traffic flow status information, and current speed into account, one could anticipate a considerable improvement in energy-saving.
The major validating approach widely adopted for energy management algorithms nowadays is real-world vehicle testing, of which the economic and time costs are relatively high. Moreover, with advanced algorithms featuring AI coming into light, putting forward higher requirement in the richness of test cases, the drawback in coverage of vehicle testing is revealed.
This paper proposed a MIL/SIL testing approach for predictive energy management algorithms, providing an alternative to, and overcome the limitations of, vehicle testing.
In the testing setup, random traffic would be generated by MATLAB based on real-time traffic condition queried from map API's, after which all the actors, apart from ego vehicle, will be taken over by SUMO.
While the scenario is running, a map sensor will fetch required properties by the algorithm at pre-sampled feature points on the planned trajectory of ego vehicle. The collected data include distances to ego vehicle, slopes of ground, speed limits at corresponding lane, traffic flow densities, average speeds, etc.. Within which the static data will be provided by a high-fidelity map hosted in RoadRunner, runtime information is computed from the status of target vehicles in the scenario on-the-fly.
The behavior of ego vehicle is emulated by vehicle dynamics block in Simulink. When ego vehicle is moving forward, all the data will be updated accordingly.
The aforementioned testing approach can, in algorithm validation, not only save cost, but also offer the possibility of scenario variation, therefore enriched test case base, and set the foundation for further analysis on impact of performance of different factors.