Generating causal explanations of vehicular agent behavioural interactions with learnt reward profiles

Howard, Rhys P M; Hawes, Nick; Kunze, Lars

Abstract

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.

• Presentation Conference Type: Conference Paper (unpublished)
• Conference Name: IEEE International Conference on Robotics and Automation (ICRA)
• Start Date: May 19, 2025
• End Date: May 23, 2025
• Acceptance Date: Jan 27, 2025
• Deposit Date: Apr 14, 2025
• Peer Reviewed: Peer Reviewed
• Public URL: https://uwe-repository.worktribe.com/output/14304679