Autonomous Driving System based on Dual Process Theory and Deliberate Practice Theory
Preprint
- 7 March 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Autonomous driving (AD), despite significant progress, is still not widely applied in open, unconstrained environments, primarily owing to deficiencies in hazard perception, few-shot generalization, corner case generalization, and evaluation metrics, resulting in reliability concerns. Therefore, we propose CogniDrive, an innovative framework based on dual-process and deliberate practice theories, leveraging contextual reasoning of the large language model (LLM) to enhance AD robustness and generalization. Inspired by dual-process theory, CogniDrive comprises two cognition modes: InstinctNav for rapid, intuitive decision-making and ReflectPlan for reflective reasoning. Enhanced by a thought model and experience embedding for LLM, InstinctNav combines behavioral cloning and retrieval augmented generation to enhance few-shot learning efficiency based on deliberate practice theory. ReflectPlan processes and internalizes reward signals embedded in language tokens within the prompt, derived from a self-reflection mechanism, to enable continuous improvement and generalization. To detect hazards in corner cases precluded by limited training data distribution, a vision language model is integrated for comprehensive environmental understanding through multimodal self-reflection. Furthermore, we propose an evaluation system that addresses the incompleteness of traditional metrics and emphasizes safety, comfort, and energy efficiency. Experiments on nuScenes and CODA datasets using the proposed evaluation system demonstrate CogniDrive's superior robustness and adaptability.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- The rise and potential of large language model based agents: a surveyScience China Information Sciences, 2025
- Pre-trained multimodal large language model enhances dermatological diagnosis using SkinGPT-4Nature Communications, 2024
- Microwave-transparent metallic metamaterials for autonomous driving safetyNature Communications, 2024
- Rebound effects undermine carbon footprint reduction potential of autonomous electric vehiclesNature Communications, 2023
- Towards artificial general intelligence via a multimodal foundation modelNature Communications, 2022
- A review on current advances in the energy and environmental performance of buildings towards a more sustainable built environmentRenewable and Sustainable Energy Reviews, 2017
- An Overview of Current Methods for Thermal Comfort Assessment in Vehicle CabinEnergy Procedia, 2016
- In two minds: dual-process accounts of reasoningTrends in Cognitive Sciences, 2003
- Extended time-to-collision measures for road traffic safety assessmentAccident Analysis & Prevention, 2001
- Artificial neural networks: fundamentals, computing, design, and applicationJournal of Microbiological Methods, 2000