Explainability of Intelligent Transportation Systems using Knowledge Compilation: a Traffic Light Controller Case
This provides explainability for automated traffic light controllers, addressing safety and transparency concerns in transportation systems, but it is incremental as it applies an existing theoretical framework to a specific domain.
The authors tackled the problem of explaining decisions made by black-box controllers in intelligent transportation systems by applying Knowledge Compilation theory to build a structured representation linking states to actions, resulting in a method implemented in a traffic light control scenario that explains controller decisions based on vehicle presence.
Usage of automated controllers which make decisions on an environment are widespread and are often based on black-box models. We use Knowledge Compilation theory to bring explainability to the controller's decision given the state of the system. For this, we use simulated historical state-action data as input and build a compact and structured representation which relates states with actions. We implement this method in a Traffic Light Control scenario where the controller selects the light cycle by observing the presence (or absence) of vehicles in different regions of the incoming roads.