Journal article · 2025 · Open access

LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking

Yukai Ma, Tiantian Wei, Naiting Zhong, Jianbiao Mei, Tao Hu, Licheng Wen, Xuemeng Yang, Botian Shi, Yong Liu

IEEE Transactions on Neural Networks and Learning Systems, 37(4), 1963–1977 · Published 4 December 2025 · DOI 10.1109/tnnls.2025.3626711

Open PDFView at the publisherCite this paper

In brief

“LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking” is a 2025 journal article by Yukai Ma and 8 co-authors, published in IEEE Transactions on Neural Networks and Learning Systems. OpenAlex counts 29 citations as of 17 November 2026, which puts it in the top 2% of works published in 2025 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at arXiv (Cornell University).

Citations
29
Most cited in
2026 (21)
Field-weighted impact
5.07
References
69
Authors
9

Abstract

While autonomous driving technology has made remarkable strides, data-driven approaches still struggle with complex scenarios due to their limited reasoning capabilities. Meanwhile, knowledge-driven autonomous driving systems have evolved considerably with the popularization of visual language models. In this article, we propose LeapVAD, a novel method based on cognitive perception and dual-process thinking. Our approach implements a human-attentional mechanism to identify and focus on critical traffic elements that influence driving decisions. By characterizing these objects through comprehensive attributes-including appearance, motion patterns, and associated risks-LeapVAD achieves more effective environmental representation and streamlines the decision-making process. Furthermore, LeapVAD incorporates an innovative dual-process decision-making module mimicking the human-driving learning process. The system consists of an analytic process (System-II) that accumulates driving experience through logical reasoning and a heuristic process (System-I) that refines this knowledge via fine-tuning and few-shot learning. LeapVAD also includes reflective mechanisms and a growing memory bank, enabling it to learn from past mistakes and continuously improve its performance in a closed-loop environment. To enhance efficiency, we develop a scene encoder network that generates compact scene representations for rapid retrieval of relevant driving experiences. Extensive evaluations conducted on two leading autonomous driving simulators, CARLA and DriveArena, demonstrate that LeapVAD achieves superior performance compared with camera-only approaches despite limited training data. Comprehensive ablation studies further emphasize its effectiveness in continuous learning and domain adaptation. Project page: https://pjlab-adg.github.io/LeapVAD/.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ma, Y., Wei, T., Zhong, N., Mei, J., Hu, T., Wen, L., Yang, X., Shi, B., & Liu, Y. (2025). LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking. IEEE Transactions on Neural Networks and Learning Systems, 37(4), 1963–1977. https://doi.org/10.1109/tnnls.2025.3626711

MLA 9

Ma, Yukai, et al. “LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking.” IEEE Transactions on Neural Networks and Learning Systems, vol. 37, no. 4, 2025, pp. 1963–1977. https://doi.org/10.1109/tnnls.2025.3626711.

Chicago

Ma, Yukai, Tiantian Wei, Naiting Zhong, Jianbiao Mei, Tao Hu, Licheng Wen, Xuemeng Yang, Botian Shi, and Yong Liu. 2025. “LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking.” IEEE Transactions on Neural Networks and Learning Systems 37 (4): 1963–1977. https://doi.org/10.1109/tnnls.2025.3626711.

Harvard

Ma, Y. et al. (2025) ‘LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking’, IEEE Transactions on Neural Networks and Learning Systems, 37(4), pp. 1963–1977. doi:10.1109/tnnls.2025.3626711.

IEEE

Y. Ma et al., “LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking,” IEEE Transactions on Neural Networks and Learning Systems, vol. 37, no. 4, pp. 1963–1977, 2025, doi: 10.1109/tnnls.2025.3626711.

BibTeX

@article{ma2025leapvad,
  title     = {{LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking}},
  author    = {Ma, Yukai and Wei, Tiantian and Zhong, Naiting and Mei, Jianbiao and Hu, Tao and Wen, Licheng and Yang, Xuemeng and Shi, Botian and Liu, Yong},
  journal   = {IEEE Transactions on Neural Networks and Learning Systems},
  year      = {2025},
  volume    = {37},
  number    = {4},
  pages     = {1963--1977},
  doi       = {10.1109/tnnls.2025.3626711},
  url       = {https://doi.org/10.1109/tnnls.2025.3626711}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety

  • autonomous driving
  • cognitive perception
  • dual-process decision making
  • vision-language models
  • few-shot learning
  • continuous learning
  • domain adaptation
  • CARLA

Work with this paper

Most-cited papers in Engineering

All highly cited Engineering papers

Questions about this paper

How do I cite this paper in APA style?

Ma, Y., Wei, T., Zhong, N., Mei, J., Hu, T., Wen, L., Yang, X., Shi, B., & Liu, Y. (2025). LeapVAD: A Leap in Autonomous Driving via Cognitive Perception and Dual-Process Thinking. IEEE Transactions on Neural Networks and Learning Systems, 37(4), 1963–1977. https://doi.org/10.1109/tnnls.2025.3626711

How many times has this paper been cited?

29 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Yukai Ma, Tiantian Wei, Naiting Zhong, Jianbiao Mei, Tao Hu, Licheng Wen, Xuemeng Yang, Botian Shi, Yong Liu.

What is the DOI of this paper?

10.1109/tnnls.2025.3626711, permanently at https://doi.org/10.1109/tnnls.2025.3626711. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.