Toward Informed AV Decision-Making: Computational Model of Well-being and Trust in Mobility

2025-05-21

AI Summary

This study addresses the insufficient modeling of human cognitive states in human–autonomous vehicle (AV) collaborative interaction. Methodologically, it proposes a human-centered, interpretable dynamic decision-making framework that jointly models the user’s and surrounding road users’ well-being and trust as real-time inferable cognitive states. A Dynamic Bayesian Network with Causal Inference Modeling (DBN-CIM) is developed and integrated into the AV’s closed-loop decision architecture. Contributions include: (1) shifting from conventional function-oriented design to multi-agent welfare as the primary optimization objective; and (2) enabling cognitive-state-driven trade-offs among user trust/well-being, third-party safety, and system cost. Empirical evaluation demonstrates significant improvements in cognitive state prediction accuracy, alongside concurrent enhancements in user trust, subjective well-being, and third-party safety in simulation.

Technology Category

• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: State Estimation

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

For future human-autonomous vehicle (AV) interactions to be effective and smooth, human-aware systems that analyze and align human needs with automation decisions are essential. Achieving this requires systems that account for human cognitive states. We present a novel computational model in the form of a Dynamic Bayesian Network (DBN) that infers the cognitive states of both AV users and other road users, integrating this information into the AV's decision-making process. Specifically, our model captures the well-being of both an AV user and an interacting road user as cognitive states alongside trust. Our DBN models infer beliefs over the AV user's evolving well-being, trust, and intention states, as well as the possible well-being of other road users, based on observed interaction experiences. Using data collected from an interaction study, we refine the model parameters and empirically assess its performance. Finally, we extend our model into a causal inference model (CIM) framework for AV decision-making, enabling the AV to enhance user well-being and trust while balancing these factors with its own operational costs and the well-being of interacting road users. Our evaluation demonstrates the model's effectiveness in accurately predicting user's states and guiding informed, human-centered AV decisions.

Problem

• Modeling human cognitive states for AV decision-making
• Balancing user well-being, trust, and operational costs
• Predicting user states to guide human-centered AV decisions

Innovation

• Dynamic Bayesian Network models cognitive states
• Integrates well-being and trust into AV decisions
• Causal inference framework balances multiple factors