Towards Safer Autonomous Driving in an Open World: A Dual-Process Approach

2026-10-02

AI Summary

This study addresses the safety and regulatory compliance deficiencies of autonomous driving in out-of-distribution scenarios by proposing a planning framework grounded in dual-process theory. The framework integrates intuitive neural network-based planning with deliberative Model Predictive Control (MPC), incorporating a metacognitive mechanism and knowledge graphs to quantify contextual risk fields. This design enables dynamic switching between the two modes to handle unfamiliar road conditions. Experimental evaluations in the CARLA simulator demonstrate that the proposed approach reduces collision rates by 89% while significantly improving compliance with complex right-of-way regulations. By effectively balancing computational efficiency and operational safety, this work establishes a novel paradigm for autonomous driving in open-world environments.

Abstract

Before autonomous driving systems can be deployed on public roads, it is vital that these systems comply with safety standards, traffic rules, and social norms. Although neural networks trained on large amounts of driving data perform well in routine driving tasks, these models often struggle in novel situations that are not well-represented in the data. In this work, we propose a novel framework that combines a neural network for intuitive, learning-based planning in routine driving tasks with model predictive control for reasoning-based planning in unfamiliar situations, inspired by Dual Process Theory. A meta-cognitive component is designed to switch between the two, using a knowledge graph to reason about contextual risk based on explicit perceptual information and relevant traffic rules and social norms. Contextual risk is represented through risk fields, guiding both the switching mechanism in the meta-cognitive component and compliance with safety standards, traffic rules, and social norms in the reasoning-based planner. The effectiveness of our framework is tested in CARLA for variations of a typical out-of-distribution situations involving (emergency) vehicles running a red light. We show that the novel architecture reduces the number of collisions in the scenarios by 89% and improves compliance with the special right-of-way rules, compared to the NN-only planner.

Problem

• Autonomous Driving
• Out-of-Distribution
• Safety Compliance
• Open World
• Traffic Rules

Innovation

• Dual Process Theory
• Model Predictive Control
• Knowledge Graph
• Risk Fields
• Out-of-Distribution