Estimating cognitive biases with attention-aware inverse planning

2025-10-29

AI Summary

This study addresses the problem of computationally estimating attention-related cognitive biases from human behavioral data to enhance autonomous systems’ (e.g., autonomous vehicles) understanding and adaptation to human behavior. To this end, we propose the Attention-Aware Inverse Planning (AAIP) framework: (1) we formally define the problem and rigorously characterize its distinguishing features—particularly its departure from conventional inverse reinforcement learning; (2) we integrate deep reinforcement learning with computational cognitive models to construct an interpretable mechanism for inferring cognitive biases; and (3) we design a scalable behavioral analysis pipeline grounded in real-world driving scenarios from the Waymo Open Dataset. Experiments successfully reconstruct and quantify drivers’ attention allocation strategies under complex tasks, demonstrating the method’s effectiveness, interpretability, and scalability in modeling cognitive biases within large-scale, realistic environments.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

People's goal-directed behaviors are influenced by their cognitive biases, and autonomous systems that interact with people should be aware of this. For example, people's attention to objects in their environment will be biased in a way that systematically affects how they perform everyday tasks such as driving to work. Here, building on recent work in computational cognitive science, we formally articulate the attention-aware inverse planning problem, in which the goal is to estimate a person's attentional biases from their actions. We demonstrate how attention-aware inverse planning systematically differs from standard inverse reinforcement learning and how cognitive biases can be inferred from behavior. Finally, we present an approach to attention-aware inverse planning that combines deep reinforcement learning with computational cognitive modeling. We use this approach to infer the attentional strategies of RL agents in real-life driving scenarios selected from the Waymo Open Dataset, demonstrating the scalability of estimating cognitive biases with attention-aware inverse planning.

Problem

• Estimating cognitive biases from human goal-directed behaviors using attention-aware inverse planning
• Inferring attentional strategies from actions in real-life driving scenarios
• Differentiating attention-aware inverse planning from standard inverse reinforcement learning

Innovation

• Estimates cognitive biases via attention-aware inverse planning
• Combines deep reinforcement learning with cognitive modeling
• Infers attentional strategies from real-world driving scenarios