Free Energy-Inspired Cognitive Risk Integration for AV Navigation in Pedestrian-Rich Environments

2025-07-28

AI Summary

Autonomous vehicles (AVs) struggle to achieve human-like prediction and decision-making in dense pedestrian scenarios, as existing approaches are primarily designed for small-scale robots and yield rigid, non-responsive pedestrian behaviors in multi-agent simulation. Method: This paper proposes an interaction modeling framework integrating cognitive uncertainty and physical risk. It innovatively incorporates a cognitive-risk integration mechanism grounded in the free-energy principle to construct a bidirectional cognitive model. Coupled with cognitive-risk-aware social forces, graph convolutional networks, and Soft Actor-Critic, it designs a risk-perceptive dynamic adjacency matrix for adaptive decision-making. Results: Experiments demonstrate significant improvements over state-of-the-art methods in safety, navigation efficiency, and trajectory smoothness, validating the framework’s effectiveness in complex, interactive urban environments.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Multiagent Systems: Adversarial Agents

Application Category

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

Abstract

Recent advances in autonomous vehicle (AV) behavior planning have shown impressive social interaction capabilities when interacting with other road users. However, achieving human-like prediction and decision-making in interactions with vulnerable road users remains a key challenge in complex multi-agent interactive environments. Existing research focuses primarily on crowd navigation for small mobile robots, which cannot be directly applied to AVs due to inherent differences in their decision-making strategies and dynamic boundaries. Moreover, pedestrians in these multi-agent simulations follow fixed behavior patterns that cannot dynamically respond to AV actions. To overcome these limitations, this paper proposes a novel framework for modeling interactions between the AV and multiple pedestrians. In this framework, a cognitive process modeling approach inspired by the Free Energy Principle is integrated into both the AV and pedestrian models to simulate more realistic interaction dynamics. Specifically, the proposed pedestrian Cognitive-Risk Social Force Model adjusts goal-directed and repulsive forces using a fused measure of cognitive uncertainty and physical risk to produce human-like trajectories. Meanwhile, the AV leverages this fused risk to construct a dynamic, risk-aware adjacency matrix for a Graph Convolutional Network within a Soft Actor-Critic architecture, allowing it to make more reasonable and informed decisions. Simulation results indicate that our proposed framework effectively improves safety, efficiency, and smoothness of AV navigation compared to the state-of-the-art method.

Problem

• Achieving human-like AV decision-making with pedestrians
• Modeling dynamic AV-pedestrian interactions realistically
• Improving AV navigation safety and efficiency

Innovation

• Free Energy Principle for cognitive modeling
• Cognitive-Risk Social Force Model for pedestrians
• Graph Convolutional Network with dynamic risk