FASIONAD : FAst and Slow FusION Thinking Systems for Human-Like Autonomous Driving with Adaptive Feedback

TL;DR

FASIONAD introduces a dual-system autonomous driving framework inspired by human cognition, combining rapid routine navigation with slow, complex reasoning, using adaptive feedback and a new benchmark for evaluation.

Contribution

The paper presents FASIONAD, a novel dual-system approach for autonomous driving that integrates fast and slow reasoning inspired by cognitive models, with a dynamic switching mechanism and a new benchmark.

Findings

Achieves state-of-the-art performance on the new nuScenes-based benchmark.

Effectively differentiates between fast and slow driving scenarios.

Enhances decision-making with adaptive feedback and human-like reasoning.

Abstract

Ensuring safe, comfortable, and efficient navigation is a critical goal for autonomous driving systems. While end-to-end models trained on large-scale datasets excel in common driving scenarios, they often struggle with rare, long-tail events. Recent progress in large language models (LLMs) has introduced enhanced reasoning capabilities, but their computational demands pose challenges for real-time decision-making and precise planning. This paper presents FASIONAD, a novel dual-system framework inspired by the cognitive model "Thinking, Fast and Slow." The fast system handles routine navigation tasks using rapid, data-driven path planning, while the slow system focuses on complex reasoning and decision-making in challenging or unfamiliar situations. A dynamic switching mechanism based on score distribution and feedback allows seamless transitions between the two systems. Visual prompts generated by the fast system enable human-like reasoning in the slow system, which provides high-quality feedback to enhance the fast system's decision-making. To evaluate FASIONAD, we introduce a new benchmark derived from the nuScenes dataset, specifically designed to differentiate fast and slow scenarios. FASIONAD achieves state-of-the-art performance on this benchmark, establishing a new standard for frameworks integrating fast and slow cognitive processes in autonomous driving. This approach paves the way for more adaptive, human-like autonomous driving systems.