Journal article · 2024 · Open access

Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety

Haochong Chen, Xincheng Cao, Levent Güvenç, Bilin Aksun Guvenc

Electronics, 13(10), 1952 · Published 16 May 2024 · DOI 10.3390/electronics13101952

Open PDFView at the publisherCite this paper

In brief

“Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety” is a 2024 journal article by Haochong Chen and 3 co-authors, published in Electronics. OpenAlex counts 39 citations as of 22 November 2026, which puts it in the top 8% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at Electronics.

Citations
39
Most cited in
2025 (21)
Field-weighted impact
3.33
References
34
Authors
4

Abstract

The application of autonomous driving system (ADS) technology can significantly reduce potential accidents involving vulnerable road users (VRUs) due to driver error. This paper proposes a novel hierarchical deep reinforcement learning (DRL) framework for high-performance collision avoidance, which enables the automated driving agent to perform collision avoidance maneuvers while maintaining appropriate speeds and acceptable social distancing. The novelty of the DRL method proposed here is its ability to accommodate dynamic obstacle avoidance, which is necessary as pedestrians are moving dynamically in their interactions with nearby ADSs. This is an improvement over existing DRL frameworks that have only been developed and demonstrated for stationary obstacle avoidance problems. The hybrid A* path searching algorithm is first applied to calculate a pre-defined path marked by waypoints, and a low-level path-following controller is used under cases where no VRUs are detected. Upon detection of any VRUs, however, a high-level DRL collision avoidance controller is activated to prompt the vehicle to either decelerate or change its trajectory to prevent potential collisions. The CARLA simulator is used to train the proposed DRL collision avoidance controller, and virtual raw sensor data are utilized to enhance the realism of the simulations. The model-in-the-loop (MIL) methodology is utilized to assess the efficacy of the proposed DRL ADS routine. In comparison to the traditional DRL end-to-end approach, which combines high-level decision making with low-level control, the proposed hierarchical DRL agents demonstrate superior performance.

Cite this paper

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

APA 7

Chen, H., Cao, X., Güvenç, L., & Guvenc, B. A. (2024). Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety. Electronics, 13(10), 1952. https://doi.org/10.3390/electronics13101952

MLA 9

Chen, Haochong, et al. “Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety.” Electronics, vol. 13, no. 10, 2024, p. 1952. https://doi.org/10.3390/electronics13101952.

Chicago

Chen, Haochong, Xincheng Cao, Levent Güvenç, and Bilin Aksun Guvenc. 2024. “Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety.” Electronics 13 (10): 1952. https://doi.org/10.3390/electronics13101952.

Harvard

Chen, H. et al. (2024) ‘Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety’, Electronics, 13(10), p. 1952. doi:10.3390/electronics13101952.

IEEE

H. Chen, X. Cao, L. Güvenç, and B. A. Guvenc, “Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety,” Electronics, vol. 13, no. 10, p. 1952, 2024, doi: 10.3390/electronics13101952.

BibTeX

@article{chen2024deep,
  title     = {{Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety}},
  author    = {Chen, Haochong and Cao, Xincheng and Güvenç, Levent and Guvenc, Bilin Aksun},
  journal   = {Electronics},
  year      = {2024},
  volume    = {13},
  number    = {10},
  pages     = {1952},
  doi       = {10.3390/electronics13101952},
  url       = {https://doi.org/10.3390/electronics13101952}
}

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

Citations by year

YearCitationsShare of the best year
202422
20252121
20261616

Its field-weighted citation impact is 3.33: it has been cited 3.33 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

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

  • collision avoidance
  • autonomous driving
  • vulnerable road users
  • pedestrian safety
  • hierarchical deep reinforcement learning
  • dynamic obstacle avoidance
  • path following control
  • social distancing

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?

Chen, H., Cao, X., Güvenç, L., & Guvenc, B. A. (2024). Deep-Reinforcement-Learning-Based Collision Avoidance of Autonomous Driving System for Vulnerable Road User Safety. Electronics, 13(10), 1952. https://doi.org/10.3390/electronics13101952

How many times has this paper been cited?

39 times, according to OpenAlex on 22 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 Electronics: sign in and open the PDF from this page.

Who wrote this paper?

Haochong Chen, Xincheng Cao, Levent Güvenç, Bilin Aksun Guvenc.

What is the DOI of this paper?

10.3390/electronics13101952, permanently at https://doi.org/10.3390/electronics13101952. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 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.