Autonomous driving system based on dual process theory and deliberate practice theory
Open Access
- 22 April 2026
- journal article
- Published by Springer Nature in Nature Communications
- Vol. 17
Abstract
Autonomous driving, 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. To address these challenges, we propose CogniDrive, a framework based on dual-process and deliberate practice theories, leveraging contextual reasoning of the Large Language Model (LLM) to enhance driving systems 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. We further propose an evaluation framework that complements traditional metrics by emphasizing safety, comfort, and energy efficiency, and demonstrate state-of-the-art performance through extensive open-loop and closed-loop experiments.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (U25B20273)
- National Science and Technology Major Project
- Beijing Natural Science Foundation
This publication has 46 references indexed in Scilit:
- On the evolution of polysensory superior temporal sulcus and middle temporal gyrus: A key component of the semantic system in the human brainJournal of Comparative Neurology, 2023
- Differentiable Raycasting for Self-Supervised Occupancy Forecasting2022
- CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving2022
- ST-P3: End-to-End Vision-Based Autonomous Driving via Spatial-Temporal Feature Learning2022
- Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D2020
- 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