New method for automatic and efficient discovery of reliable gas turbine system designs
— Exploiting the logical specification in black box optimization and applying it to the design process of real commercial products — A research team consisting mainly of SATO Sota and HASUO Ichiro at the National Institute of Informatics (NII, Japan) and the Graduate University for Advanced Studies (SOKENDAI, Japan), developed a method for automatically finding gas turbine control system designs that satisfy multiple requirements, with collaboration of Mitsubishi Heavy Industries, Ltd.
Automatic control system design methods have not hitherto been able to discover controllers of comparable quality to those designed by human experts. But with the new method developed by this research team, it is now possible to find controllers with comparable quality to the results obtained manually by human experts, based on fully automatic computation. This method is generally applicable to “black box” control systems whose internal behavior cannot be described by models such as mathematical formulas. The method is expected to be useful in design processes in various fields such as autonomous driving.
This research was conducted under the ERATO MMSD Project（*1） funded by the Japan Science and Technology Agency (JST, Japan). The results of this research will be presented online on November 24, 2021 (Chinese Standard Time) at the 24th International Formal Methods Symposium (FM’21).
A team consisting of Ezequiel Castellano, Ahmet Cetinkaya, Cédric Ho Thanh, Stefan Klikovits, Xiaoyi Zhang, and Paolo Arcaini, submitted the Frenetic tool to the CPS testing competition of SBST 2021 which showed good results in terms of diversity and failure generation rate.
The competition focused on the scenario generation for testing the lane-keeping capabilities of an autonomous driving system, using the BeamNG simulator. The goal was to generate virtual roads that lead to lane-keeping failures (a.k.a. OBEs, for Out-of-Bounds-Errors) within a certain time frame. The submitted tools competed in two distinct configurations, differing in time budget, vehicle configuration, and OBE tolerance.
Frenetic is a genetic approach that leverages a curvature-based road representation, and introduces some nuances aiming at improving diversity of the generated roads.
Implementations were not ranked, but the competition report (in print) states that Frenetic is generally “very effective and triggered many failures“. In fact, Frenetic was among the two tools that “triggered at least 10x more OBEs than the other tools for both configurations”. In particular, “Frenetic exposed the most diverse set of failures on average” and found ”the highest number of OBEs for which the ego-car invades the opposite traffic lane”, which might be of particular interest for car manufacturers.* The Frenetic implementation and a description of the algorithm are available in our repository.