Large Language Models for Intelligent Transportation: A Review of the State of the Art and Challenges
Source abstract
Abstract
Large Language Models (LLMs), based on their highly developed ability to comprehend and generate human-like text, promise to revolutionize all aspects of society. These LLMs facilitate complex language understanding, translation, content generation, and problem-solving, enabled by vast historical data processing and fine-tuning. Throughout the past year, with the initial release of ChatGPT to the public, many papers have appeared on how to exploit LLMs for the ways we operate and interact with intelligent transportation systems. In this study, we review more than 130 papers on the subject and group them according to their major contributions into the following five categories: autonomous driving, safety, tourism, traffic, and others. Based on the aggregated proposals and findings in the extant literature, this paper concludes with a set of challenges and research recommendations, hopefully contributing to guide research in this young, yet extremely active research domain.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Topic Modeling · Traffic Prediction and Management Techniques · Advanced Text Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
State Key Lab of CNS/ATM, Beihang University, Beijing 100191, China
Funding
Beijing Natural Science Foundation · National Natural Science Foundation of China
References (100+)
Show source-provided references
1. SPSRec: An Efficient Signal Phase Recommendation for Signalized Intersections With GAN and Decision-Tree Model10.1109/TITS.2022.3207815 ↗
2. Distracted Driver Detection Based on a CNN With Decreasing Filter Size10.1109/TITS.2021.3063521 ↗
3. A Hybrid Driving Decision-Making System Integrating Markov Logic Networks and Connectionist AI10.1109/TITS.2022.3227122 ↗
4. Machine Learning to Solve Vehicle Routing Problems: A Survey10.1109/TITS.2023.3334976 ↗
5. Decoding Urban Mobility: Application of Natural Language Processing and Machine Learning to Activity Pattern Recognition, Prediction, and Temporal Transferability Examination10.1109/TITS.2023.3339772 ↗
6. Travel Mode Choice Prediction Using Imbalanced Machine Learning10.1109/TITS.2023.3237681 ↗
7. Ensemble Deep Learning for Sustainable Multimodal UAV Classification10.1109/TITS.2022.3170643 ↗
8. Integrating AI support into a framework for collaborative decision-making (CDM) for airline disruption management10.1016/j.jatrs.2024.100026 ↗
9. Artificial Intelligence as a driver of efficiency in air passenger transport: A systematic literature review and future research avenues10.1016/j.jatrs.2024.100030 ↗
10. Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., and Metzler, D. (2022). Emergent abilities of Large Language Models. arXiv.
11. Towards artificial general intelligence via a multimodal foundation model10.1038/s41467-022-30761-2 ↗
12. Bubeck, S., Chandrasekaran, V., Eldan, R., Gehrke, J., Horvitz, E., Kamar, E., Lee, P., Lee, Y.T., Li, Y., and Lundberg, S. (2023). Sparks of artificial general intelligence: Early experiments with gpt-4. arXiv.
13. Gpt-4 passes the bar exam10.1098/rsta.2023.0254 ↗
14. Liu, X., Zheng, Y., Du, Z., Ding, M., Qian, Y., Yang, Z., and Tang, J. GPT understands, too. AI Open, 2023.10.1016/j.aiopen.2023.08.012 ↗
15. Large language models for air transportation: A critical review10.1016/j.jatrs.2024.100024 ↗
16. Language models are unsupervised multitask learners
17. Language models are few-shot learners
18. Recent advances in natural language processing via large pre-trained language models: A survey10.1145/3605943 ↗
19. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017, January 4–9). Attention is all you need. Proceedings of the 31st Conference on Neural Information Processing Systems, Long Beach, CA, USA.
20. Feedback is all you need: From ChatGPT to autonomous driving10.1007/s11432-023-3740-x ↗
21. DriveLLM: Charting the Path toward Full Autonomous Driving with Large Language Models10.1109/TIV.2023.3327715 ↗
22. Cui, C., Ma, Y., Cao, X., Ye, W., Zhou, Y., Liang, K., Chen, J., Lu, J., Yang, Z., and Liao, K.D. (2023). A Survey on Multimodal Large Language Models for Autonomous Driving. arXiv.10.1109/WACVW60836.2024.00106 ↗
23. Deng, Y., Yao, J., Tu, Z., Zheng, X., Zhang, M., and Zhang, T. (2023). TARGET: Traffic Rule-based Test Generation for Autonomous Driving Systems. arXiv.
24. Dewangan, V., Choudhary, T., Chandhok, S., Priyadarshan, S., Jain, A., Singh, A.K., Srivastava, S., Jatavallabhula, K.M., and Krishna, K.M. (2023). Talk2BEV: Language-enhanced Bird’s-eye View Maps for Autonomous Driving. arXiv.10.1109/ICRA57147.2024.10611485 ↗
25. Chat with chatgpt on intelligent vehicles: An IEEE tiv perspective10.1109/TIV.2023.3253281 ↗
26. Fu, D., Li, X., Wen, L., Dou, M., Cai, P., Shi, B., and Qiao, Y. (2023). Drive like a human: Rethinking autonomous driving with large language models. arXiv.10.1109/WACVW60836.2024.00102 ↗
27. ChatGPT in connected and autonomous vehicles: Benefits and challenges10.20517/ir.2023.08 ↗
28. Sha, H., Mu, Y., Jiang, Y., Chen, L., Xu, C., Luo, P., Li, S.E., Tomizuka, M., Zhan, W., and Ding, M. (2023). Languagempc: Large language models as decision makers for autonomous driving. arXiv.
29. Leveraging ChatGPT for Real-Time Decision-Making in Autonomous Systems
30. VistaGPT: Generative Parallel Transformers for Vehicles With Intelligent Systems for Transport Automation10.1109/TIV.2023.3307012 ↗
31. Wang, Y., Jiao, R., Lang, C., Zhan, S.S., Huang, C., Wang, Z., Yang, Z., and Zhu, Q. (2023). Empowering Autonomous Driving with Large Language Models: A Safety Perspective. arXiv.
32. Wen, L., Fu, D., Li, X., Cai, X., Ma, T., Cai, P., Dou, M., Shi, B., He, L., and Qiao, Y. (2023). Dilu: A knowledge-driven approach to autonomous driving with large language models. arXiv.
33. Xu, Z., Zhang, Y., Xie, E., Zhao, Z., Guo, Y., Wong, K.K., Li, Z., and Zhao, H. (2023). Drivegpt4: Interpretable end-to-end autonomous driving via large language model. arXiv.10.1109/LRA.2024.3440097 ↗
34. Yang, Z., Jia, X., Li, H., and Yan, J. (2023). A Survey of Large Language Models for Autonomous Driving. arXiv.
35. Zhao, Y., Li, Z., Jin, Z., Zhang, F., Zhao, H., Dou, C., Tao, Z., Xu, X., and Liu, D. (2023). Enhancing the Spatial Awareness Capability of Multi-Modal Large Language Model. arXiv.
36. Zhou, X., Liu, M., Zagar, B.L., Yurtsever, E., and Knoll, A.C. (2023). Vision language models in autonomous driving and intelligent transportation systems. arXiv.10.1109/TIV.2024.3402136 ↗
37. Andrade, S.R., and Walsh, H.S. (2023, January 12–16). SafeAeroBERT: Towards a Safety-Informed Aerospace-Specific Language Model. Proceedings of the AIAA AVIATION 2023 Forum, San Diego, CA, USA.10.2514/6.2023-3437 ↗
38. Arteaga, C., and Park, J.W. (2023, November 22). A Large Language Model Framework to Uncover Underreporting in Traffic Crashes. Available online: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4613378.10.2139/ssrn.4613378 ↗
39. Chandra, C., Jing, X., Bendarkar, M.V., Sawant, K., Elias, L., Kirby, M., and Mavris, D.N. (2023, January 12–16). Aviation-BERT: A Preliminary Aviation-Specific Natural Language Model. Proceedings of the AIAA AVIATION 2023 Forum, San Diego, CA, USA.10.2514/6.2023-3436 ↗
40. ERNIE-based Named Entity Recognition Method for Traffic Accident Cases
41. de Zarzà, I., de Curtò, J., Roig, G., and Calafate, C.T. (2023). LLM multimodal traffic accident forecasting. Sensors, 23.10.3390/s23229225 ↗
42. Identifying incident causal factors to improve aviation transportation safety: Proposing a deep learning approach10.1155/2021/5540046 ↗
43. Jing, X., Chennakesavan, A., Chandra, C., Bendarkar, M.V., Kirby, M., and Mavris, D.N. (2023, January 12–16). BERT for Aviation Text Classification. Proceedings of the AIAA AVIATION 2023 Forum, San Diego, CA, USA.10.2514/6.2023-3438 ↗
44. Kierszbaum, S., Klein, T., and Lapasset, L. (2022). ASRS-CMFS vs. RoBERTa: Comparing Two Pre-Trained Language Models to Predict Anomalies in Aviation Occurrence Reports with a Low Volume of In-Domain Data Available. Aerospace, 9.10.3390/aerospace9100591 ↗
45. Mumtarin, M., Chowdhury, M.S., and Wood, J. (2023). Large Language Models in Analyzing Crash Narratives—A Comparative Study of ChatGPT, BARD and GPT-4. arXiv.
46. Raja, K.V., Siddharth, R., Yuvaraj, S., and Kumar, K.R. An Artificial Intelligence based automated case-based reasoning (CBR) system for severity investigation and root-cause analysis of road accidents–Comparative analysis with the predictions of ChatGPT. J. Eng. Res., 2023.
47. Tikayat Ray, A., Bhat, A.P., White, R.T., Nguyen, V.M., Pinon Fischer, O.J., and Mavris, D.N. (2023). Examining the Potential of Generative Language Models for Aviation Safety Analysis: Case Study and Insights Using the Aviation Safety Reporting System (ASRS). Aerospace, 10.10.20944/preprints202307.0192.v1 ↗
48. Yang, C., and Huang, C. (2023). Natural Language Processing (NLP) in Aviation Safety: Systematic Review of Research and Outlook into the Future. Aerospace, 10.10.3390/aerospace10070600 ↗
49. Zheng, O., Abdel-Aty, M., Wang, D., Wang, C., and Ding, S. (2023). TrafficSafetyGPT: Tuning a Pre-trained Large Language Model to a Domain-Specific Expert in Transportation Safety. arXiv.
50. Zheng, O., Abdel-Aty, M., Wang, D., Wang, Z., and Ding, S. (2023). ChatGPT is on the horizon: Could a Large Language Model be all we need for Intelligent Transportation?. arXiv.
51. Artificial Intelligence applications in aviation accident classification: A preliminary exploratory study10.1016/j.dajour.2023.100358 ↗
52. Antecedents and consequences of travelers’ trust towards personalized travel recommendations offered by ChatGPT10.1016/j.ijhm.2023.103588 ↗
53. ChatGPT for tourism: Applications, benefits and risks10.1108/TR-02-2023-0088 ↗
54. Is ChatGPT the right technology for service individualization and value co-creation? evidence from the travel industry10.1080/10548408.2023.2255884 ↗
55. Professionals’ perspectives on ChatGPT in the tourism industry: Does it inspire awe or concern?10.24288/jttr.1313481 ↗
56. Leveraging ChatGPT and other generative Artificial Intelligence (AI)-based applications in the hospitality and tourism industry: Practices, challenges and research agenda10.1108/IJCHM-05-2023-0686 ↗
57. Importance of ChatGPT in Tourism
58. Flores-Cruz, G., Hinkle, S.D., Roque, N.A., and Mouloua, M. (2023, January 23–27). ChatGPT as the Ultimate Travel Buddy or Research Assistant: A Study on Perceived Attitudes and Usability. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Washington, DC, USA.10.1177/21695067231193678 ↗
59. Goktas, P., and Dirsehan, T. (2023, November 09). Optimizing Customer Experience in Hospitality and Tourism with ChatGPT Plugins: A Strategic Guide. Available online: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4602852.10.2139/ssrn.4602852 ↗
60. ChatGPT and the hospitality and tourism industry: An overview of current trends and future research directions
61. Overview of ChatGPT Technology and its Potential in Improving Tourism Information Services10.33395/jmp.v12i1.12416 ↗
62. Holy or unholy? Interview with open AI’s ChatGPT10.54055/ejtr.v34i.3169 ↗
63. Game of algorithms: ChatGPT implications for the future of tourism education and research10.1108/JTF-02-2023-0038 ↗
64. Kim, J.H., Kim, J., Park, J., Kim, C., Jhang, J., and King, B. (2023). When ChatGPT Gives Incorrect Answers: The Impact of Inaccurate Information by Generative AI on Tourism Decision-Making. J. Travel Res.10.1177/00472875231212996 ↗
65. Effects of AI ChatGPT on travelers’ travel decision-making10.1108/TR-07-2023-0489 ↗
66. ChatGPT for e-Tourism: A technological perspective10.1007/s40558-023-00248-x ↗
67. Nautiyal, R., Albrecht, J.N., and Nautiyal, A. (2023). ChatGPT and tourism academia. Ann. Tour. Res., 99.10.1016/j.annals.2023.103544 ↗
68. Shin, S., Kim, J., Lee, E., Yhee, Y., and Koo, C. (2023). ChatGPT for Trip Planning: The Effect of Narrowing Down Options. J. Travel Res.10.1177/00472875231214196 ↗
69. The Role of ChatGPT in Enhancing the Information Search and Decision-Making Process of Travellers10.33395/jmp.v12i1.12443 ↗
70. Autonomous travel decision-making: An early glimpse into ChatGPT and generative AI10.1016/j.jhtm.2023.06.022 ↗
71. Da, L., Gao, M., Mei, H., and Wei, H. (2023). LLM powered sim-to-real transfer for traffic signal control. arXiv.10.1109/CASE56687.2023.10260398 ↗
72. Classifying Pedestrian Maneuver Types Using the Advanced Language Model10.1177/03611981231155187 ↗
73. Putting ChatGPT Vision (GPT-4V) to the test: Risk perception in traffic images10.1098/rsos.231676 ↗
74. Guo, D., Zhang, Z., Fan, P., Zhang, J., and Yang, B. (2021). A context-aware language model to improve the speech recognition in air traffic control. Aerospace, 8.10.3390/aerospace8110348 ↗
75. TrafficBERT: Pre-trained model with large-scale data for long-range traffic flow forecasting10.1016/j.eswa.2021.115738 ↗
76. Jin, Y., Shen, X., Peng, H., Liu, X., Qin, J., Li, J., Xie, J., Gao, P., Zhou, G., and Gong, J. (2023). Surrealdriver: Designing generative driver agent simulation framework in urban contexts based on Large Language Model. arXiv.
77. Maynard, P., Clarke, S.S., Almache, J., Kumar, S., Rajkumar, S., Kemp, A., and Pai, R. (2021, January 2–6). Natural Language Processing (NLP) Techniques for Air Traffic Management Planning. Proceedings of the AIAA AVIATION 2021 Forum, Virtual.10.2514/6.2021-2322 ↗
78. Mo, B., Xu, H., Zhuang, D., Ma, R., Guo, X., and Zhao, J. (2023). Large Language Models for Travel Behavior Prediction. arXiv.
79. Qasemi, E., Francis, J.M., and Oltramari, A. (2023). Traffic-domain video question answering with automatic captioning. arXiv.
80. Enhancing Driving Experience and Safety through ChatGPT in Vehicle Systems
81. Sui, G., Li, Z., Li, Z., Yang, S., Ruan, J., Mao, H., and Zhao, R. (2023). Reboost Large Language Model-based Text-to-SQL, Text-to-Python, and Text-to-Function—With Real Applications in Traffic Domain. arXiv.
82. Tan, S., Ivanovic, B., Weng, X., Pavone, M., and Kraehenbuehl, P. (2023). Language conditioned traffic generation. arXiv.
83. Villarreal, M., Poudel, B., and Li, W. (2023). Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning. arXiv.10.1109/ITSC57777.2023.10422410 ↗
84. Wang, X., Ding, H., Xu, Q., and Liu, Z. (2022). Information Extraction of Air-Traffic Control Instructions via Pre-trained Models. Artificial Intelligence in China, Proceedings of the 3rd International Conference on Artificial Intelligence in China, 2022, Springer.10.1007/978-981-16-9423-3_11 ↗
85. ChatGPT as Your Vehicle Co-Pilot: An Initial Attempt10.1109/TIV.2023.3325300 ↗
86. Zhang, J., Ilievski, F., Ma, K., Kollaa, A., Francis, J., and Oltramari, A. (2023). A Study of Situational Reasoning for Traffic Understanding. arXiv.10.1145/3580305.3599246 ↗
87. HiVeGPT: Human-machine-augmented intelligent vehicles with generative pre-trained transformer10.1109/TIV.2023.3256982 ↗
88. Zhang, S., Fu, D., Zhang, Z., Yu, B., and Cai, P. (2023). TrafficGPT: Viewing, Processing and Interacting with Traffic Foundation Models. arXiv.10.1016/j.tranpol.2024.03.006 ↗
89. Semantic understanding and prompt engineering for large-scale traffic data imputation10.1016/j.inffus.2023.102038 ↗
90. Agarwal, A., Gawade, S., Azad, A.P., and Bhattacharyya, P. (2023). KITLM: Domain-Specific Knowledge InTegration into Language Models for Question Answering. arXiv.
91. Chew, P. (2023, December 01). Pioneering Tomorrow’s AI System through Aerospace Engineering: An Empirical Study of the Peter Chew Method for Overcoming Error in Chat GPT. Available online: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4646033.10.2139/ssrn.4646033 ↗
92. Kim, J., and Lee, J. How does ChatGPT Introduce Transport Problems and Solutions in North America?. Findings, 2023.10.32866/001c.72634 ↗
93. Leong, M., Abdelhalim, A., Ha, J., Patterson, D., Pincus, G.L., Harris, A.B., Eichler, M., and Zhao, J. (2023). MetRoBERTa: Leveraging Traditional Customer Relationship Management Data to Develop a Transit-Topic-Aware Language Model. arXiv.10.1177/03611981231225655 ↗
94. Nguyen, B., Sonnenfeld, N., Finkelstein, L., Alonso, A., Gomez, C., Duruaku, F., and Jentsch, F. (2023, January 23–27). Using AI Tools to Develop Training Materials for Aviation: Ethical, Technical, and Practical Concerns. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, Washington, DC, USA.10.1177/21695067231192904 ↗
95. Tikayat Ray, A., Cole, B.F., Pinon Fischer, O.J., White, R.T., and Mavris, D.N. (2023). aeroBERT-Classifier: Classification of Aerospace Requirements Using BERT. Aerospace, 10.10.20944/preprints202302.0077.v1 ↗
96. Tikayat Ray, A., Pinon-Fischer, O.J., Mavris, D.N., White, R.T., and Cole, B.F. (2023, January 12–16). aeroBERT-NER: Named-Entity Recognition for Aerospace Requirements Engineering using BERT. Proceedings of the AIAA SCITECH 2023 Forum, San Diego, CA, USA.10.2514/6.2023-2583 ↗
97. Voß, S. (2023). Bus Bunching and Bus Bridging: What Can We Learn from Generative AI Tools like ChatGPT?. Sustainability, 15.10.3390/su15129625 ↗
98. Wang, L., Chou, J., Rouck, D., Tien, A., and Baumgartner, D.M. (2023). Adapting Sentence Transformers for the Aviation Domain. arXiv.10.2514/6.2024-2702 ↗
99. Wang, L., Chou, J., Zhou, X., Tien, A., and Baumgartner, D.M. (2023). AviationGPT: A Large Language Model for the Aviation Domain. arXiv.
100. AirBERT: A fine-tuned language representation model for airlines tweet sentiment analysis