Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward Profiles
This work addresses transparency and explainability for autonomous vehicles interacting with humans, but it is incremental as it builds on existing causal reasoning approaches.
The paper tackled the problem of making causal inferences about autonomous vehicle agent planning by learning a weighting of reward metrics, and demonstrated functional improvement over previous methods across three real-world driving datasets.
Transparency and explainability are important features that responsible autonomous vehicles should possess, particularly when interacting with humans, and causal reasoning offers a strong basis to provide these qualities. However, even if one assumes agents act to maximise some concept of reward, it is difficult to make accurate causal inferences of agent planning without capturing what is of importance to the agent. Thus our work aims to learn a weighting of reward metrics for agents such that explanations for agent interactions can be causally inferred. We validate our approach quantitatively and qualitatively across three real-world driving datasets, demonstrating a functional improvement over previous methods and competitive performance across evaluation metrics.