CoChat
Sign Up
Cited by 3Autonomous Vehicle Technology and SafetySafety Systems Engineering in AutonomyAdvanced Software Engineering Methodologies

FIXDRIVE: Automatically Repairing Autonomous Vehicle Driving Behaviour for $0.08 per Violation

Open access
Sun, Yang, Poskitt, Christopher M., Wang, Kun, Sun, Jun·2025·2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)
DOI 10.1109/icse55347.2025.00216
Open this paper in CoChat — free accountOpen PDF

Abstract

Autonomous Vehicles (AVs) are advancing rapidly, with Level-4 AVs already operating in real-world conditions. Current AVs, however, still lag behind human drivers in adaptability and performance, often exhibiting overly conservative behaviours and occasionally violating traffic laws. Existing solutions, such as runtime enforcement, mitigate this by automatically repairing the AV's planned trajectory at runtime, but such approaches lack transparency and should be a measure of last resort. It would be preferable for AV repairs to generalise beyond specific incidents and to be interpretable for users. In this work, we propose Fixdrive, a framework that analyses driving records from near-misses or law violations to generate AV driving strategy repairs that reduce the chance of such incidents occurring again. These repairs are captured in μDrive, a high-level domain-specific language for specifying driving behaviours in response to event-based triggers. Implemented for the state-of-the-art autonomous driving system Apollo, Fixdrive identifies and visualises critical moments from driving records, then uses a Multimodal Large Language Model (MLLM) with zero-shot learning to generate μDrive programs. We tested Fixdrive on various benchmark scenarios, and found that the generated repairs improved the AV's performance with respect to following traffic laws, avoiding collisions, and successfully reaching destinations. Furthermore, the direct costs of repairing an AV—15 minutes of offline analysis and $0.08 per violation-are reasonable in practice.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/icse55347.2025.00216

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 35

  1. Z. Wan, J. Shen, J. Chuang, X. Xia, J. Garcia, J. Ma, and Q. A. Chen, "Too afraid to drive: Systematic discovery of semantic DoS vulnerability in autonomous driving planning under physical-world attacks," in NDSS. The Internet Society, 2022.
  2. S. K. Bashetty, H. B. Amor, and G. Fainekos, "DeepCrashTest: Turning dashcam videos into virtual crash tests for automated driving systems," in ICRA. IEEE, 2020, pp. 11 353-11 360.
  3. G. Li, Y. Li, S. Jha, T. Tsai, M. B. Sullivan, S. K. S. Hari, Z. Kalbarczyk, and R. K. Iyer, "AV-FUZZER: Finding safety violations in autonomous driving systems," in ISSRE. IEEE, 2020, pp. 25-36.
  4. Y. Sun, C. M. Poskitt, J. Sun, Y. Chen, and Z. Yang, "LawBreaker: An approach for specifying traffic laws and fuzzing autonomous vehicles," in ASE. ACM, 2022, pp. 62:1-62:12.
  5. Y. Zhou, Y. Sun, Y. Tang, Y. Chen, J. Sun, C. M. Poskitt, Y. Liu, and Z. Yang, "Specification-based autonomous driving system testing," IEEE Trans. Software Eng., vol. 49, no. 6, pp. 3391-3410, 2023.
  6. Y. Sun, C. M. Poskitt, X. Zhang, and J. Sun, "REDriver: Runtime enforcement for autonomous vehicles," in ICSE. ACM, 2024, pp. 176:1-176:12.
  7. J. Grieser, M. Zhang, T. Warnecke, and A. Rausch, "Assuring the safety of end-to-end learning-based autonomous driving through runtime monitoring," in DSD. IEEE, 2020, pp. 476-483.
  8. D. K. Hong, J. Kloosterman, Y. Jin, Y. Cao, Q. A. Chen, S. A. Mahlke, and Z. M. Mao, "AVGuardian: Detecting and mitigating publish- subscribe overprivilege for autonomous vehicle systems," in EuroS&P. IEEE, 2020, pp. 445-459.
  9. K. Cheng, Y. Zhou, B. Chen, R. Wang, Y. Bai, and Y. Liu, "Guardauto: A decentralized runtime protection system for autonomous driving," IEEE Trans. Computers, vol. 70, no. 10, pp. 1569-1581, 2021.
  10. S. Shankar, U. V. R, S. Pinisetty, and P. S. Roop, "Formal runtime monitoring approaches for autonomous vehicles," in OVERLAY'20, ser. CEUR Workshop Proceedings, vol. 2785. CEUR-WS.org, 2020, pp. 89-94.
  11. M. Mauritz, F. Howar, and A. Rausch, "Assuring the safety of advanced driver assistance systems through a combination of simulation and runtime monitoring," in ISoLA (2), ser. LNCS, vol. 9953, 2016, pp. 672-687.
  12. B. D'Angelo, S. Sankaranarayanan, C. Sánchez, W. Robinson, B. Finkbeiner, H. B. Sipma, S. Mehrotra, and Z. Manna, "LOLA: Run- time monitoring of synchronous systems," in TIME. IEEE Computer Society, 2005, pp. 166-174.
  13. K. Watanabe, E. Kang, C. Lin, and S. Shiraishi, "Runtime monitoring for safety of intelligent vehicles," in DAC. ACM, 2018, pp. 31:1-31:6.
  14. L. Chen, P. Wu, K. Chitta, B. Jaeger, A. Geiger, and H. Li, "End-to- end autonomous driving: Challenges and frontiers," IEEE Trans. Pattern Anal. Mach. Intell., vol. 46, no. 12, pp. 10 164-10 183, 2024.
  15. A. Prakash, K. Chitta, and A. Geiger, "Multi-modal fusion transformer for end-to-end autonomous driving," in CVPR. Computer Vision Foundation / IEEE, 2021, pp. 7077-7087.
  16. K. Sama, Y. Morales, H. Liu, N. Akai, A. Carballo, E. Takeuchi, and K. Takeda, "Extracting human-like driving behaviors from expert driver data using deep learning," IEEE Trans. Veh. Technol., vol. 69, no. 9, pp. 9315-9329, 2020.
  17. J. Wei, J. M. Dolan, and B. Litkouhi, "A learning-based autonomous driver: Emulate human driver's intelligence in low-speed car following," in Unattended Ground, Sea, and Air Sensor Technologies and Applica- tions XII, vol. 7693. SPIE, 2010, pp. 93-104.
  18. L. Xu, J. Hu, H. Jiang, and W. Meng, "Establishing style-oriented driver models by imitating human driving behaviors," IEEE Trans. Intell. Transp. Syst., vol. 16, no. 5, pp. 2522-2530, 2015.
  19. D. Xu, Z. Ding, X. He, H. Zhao, M. Moze, F. Aioun, and F. Guillemard, "Learning from naturalistic driving data for human-like autonomous highway driving," IEEE Trans. Intell. Transp. Syst., vol. 22, no. 12, pp. 7341-7354, 2021.
  20. L. Le Mero, D. Yi, M. Dianati, and A. Mouzakitis, "A survey on imitation learning techniques for end-to-end autonomous vehicles," IEEE Trans. Intell. Transp. Syst., vol. 23, no. 9, pp. 14 128-14 147, 2022.
  21. T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert- Voss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, and D. Amodei, "Language models are few-shot learners," in NeurIPS, 2020.
  22. OpenAI, "GPT-4 technical report," CoRR, vol. abs/2303.08774, 2023. · arXiv
  23. S. Yin, C. Fu, S. Zhao, K. Li, X. Sun, T. Xu, and E. Chen, "A survey on multimodal large language models," CoRR, vol. abs/2306.13549, 2023. · arXiv
  24. C. Cui, Y. Ma, X. Cao, W. Ye, Y. Zhou, K. Liang, J. Chen, J. Lu, Z. Yang, K. Liao, T. Gao, E. Li, K. Tang, Z. Cao, T. Zhou, A. Liu, X. Yan, S. Mei, J. Cao, Z. Wang, and C. Zheng, "A survey on multimodal large language models for autonomous driving," in WACV (Workshops). IEEE, 2024, pp. 958-979.
  25. L. Chen, O. Sinavski, J. Hünermann, A. Karnsund, A. J. Willmott, D. Birch, D. Maund, and J. Shotton, "Driving with LLMs: Fusing object- level vector modality for explainable autonomous driving," in ICRA. IEEE, 2024, pp. 14 093-14 100.
  26. J. Mao, Y. Qian, H. Zhao, and Y. Wang, "GPT-Driver: Learning to drive with GPT," CoRR, vol. abs/2310.01415, 2023. · arXiv
  27. L. Wen, X. Yang, D. Fu, X. Wang, P. Cai, X. Li, T. Ma, Y. Li, L. Xu, D. Shang, Z. Zhu, S. Sun, Y. Bai, X. Cai, M. Dou, S. Hu, B. Shi, and Y. Qiao, "On the road with GPT-4V(ision): Early explorations of visual- language model on autonomous driving," CoRR, vol. abs/2311.05332, 2023. · arXiv
  28. C. Le Goues, M. Dewey-Vogt, S. Forrest, and W. Weimer, "A systematic study of automated program repair: Fixing 55 out of 105 bugs for $8 each," in ICSE. IEEE Computer Society, 2012, pp. 3-13.
  29. K. Wang, C. M. Poskitt, Y. Sun, J. Sun, J. Wang, P. Cheng, and J. Chen, "µDrive: User-controlled autonomous driving," CoRR, vol. abs/2407.13201, 2024. · arXiv
  30. O. Maler and D. Nickovic, "Monitoring temporal properties of contin- uous signals," in FORMATS/FTRTFT, ser. LNCS, vol. 3253. Springer, 2004, pp. 152-166.
  31. D. Driess, F. Xia, M. S. M. Sajjadi, C. Lynch, A. Chowdhery, B. Ichter, A. Wahid, J. Tompson, Q. Vuong, T. Yu, W. Huang, Y. Chebotar, P. Sermanet, D. Duckworth, S. Levine, V. Vanhoucke, K. Hausman, M. Toussaint, K. Greff, A. Zeng, I. Mordatch, and P. Florence, "PaLM- E: An embodied multimodal language model," in ICML, ser. Proceedings of Machine Learning Research, vol. 202. PMLR, 2023, pp. 8469-8488.
  32. H. Sun, C. M. Poskitt, Y. Sun, J. Sun, and Y. Chen, "ACAV: A frame- work for automatic causality analysis in autonomous vehicle accident recordings," in ICSE. ACM, 2024, pp. 102:1-102:13.
  33. J. V. Deshmukh, A. Donzé, S. Ghosh, X. Jin, G. Juniwal, and S. A. Seshia, "Robust online monitoring of signal temporal logic," Formal Methods Syst. Des., vol. 51, no. 1, pp. 5-30, 2017.
  34. D. Nickovic and T. Yamaguchi, "RTAMT: Online robustness monitors from STL," in ATVA, ser. LNCS, vol. 12302. Springer, 2020, pp. 564- 571.
  35. J. Levinson, J. Askeland, J. Becker, J. Dolson, D. Held, S. Kammel, J. Z. Kolter, D. Langer, O. Pink, V. R. Pratt, M. Sokolsky, G. Stanek, D. M. Stavens, A. Teichman, M. Werling, and S. Thrun, "Towards fully autonomous driving: Systems and algorithms," in Intelligent Vehicles Symposium. IEEE, 2011, pp. 163-168.

Cited by

Sorted by citations

Authors
Sun, Y., Poskitt, C. M., Wang, K., & Sun, J.
Affiliations
  • Singapore Management University (SG)
  • State Key Laboratory of Industrial Control Technology (CN)
ORCID
Venue
2025 IEEE/ACM 47th International Conference on Software Engineering (ICSE)
Publisher
IEEE
Published
2025-04-26
Pages
1921-1933
ISSN
0270-5257 (ISSN-L)
DOI
10.1109/icse55347.2025.00216
OpenAlex
W4411552192
Cited by
3
References
1
Citations by year
2026: 1 · 2025: 2
FWCI
4.77
Type
conference paper
Language
en
Open access
Licence
Locations
  • ACM/IEEE International Conference on Software Engineering: Companion Proceedings (ICSE-Companion) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • Singapore Management University Institutional Knowledge (InK) (Singapore Management University) (submittedVersion, other-oa)
  • arXiv (Cornell University)
Funders
  • Ministry of Education - Singapore (Tier 3, MOET32020-0004)
  • Bộ Giáo dục và Ðào tạo
Topics
  • Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
  • Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
  • Physical Sciences › Computer Science › Artificial Intelligence › Advanced Software Engineering Methodologies
Keywords
autonomous vehicles, traffic offenses, near misses, driving records, domain-specific languages, multimodal large language models, zero-shot learning, Apollo, runtime enforcement, collision avoidance, interpretability

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review