Successfully Using ChatGPT in Logistics: Are We There Yet? | SpringerLink
Skip to main content
Springer Nature Link
Log in

Successfully Using ChatGPT in Logistics: Are We There Yet?

  • Conference paper
  • First Online:
Computational Logistics (ICCL 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14239))

Included in the following conference series:

Abstract

ChatGPT is among the recent most-commonly discussed artificial intelligence systems. While many success stories as well as misuses are exemplified in different fields like, e.g., education, the usefulness in various academic disciplines with very close ties to practical applications still needs to be proven. In this paper we explore the use of this artificial intelligence (AI) tool within the logistics domain. As a lesson learned, one has to be careful. That is, answers cannot always be granted as being correct. Beyond diving into related literature, we explore the use of ChatGPT regarding an as yet underexplored (even without consulting generative AI tools) logistics problem, that is, the stochastic vehicle routing problem with uncertainty in the number of available vehicles.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 10295
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 12869
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    See, e.g., https://openai.com/blog/chatgpt; last access 30 April 2023.

  2. 2.

    See, e.g., https://blog.google/technology/ai/bard-google-ai-search-updates/; last access 30 April 2023.

  3. 3.

    https://www.perplexity.ai/; last access 22 June 2023.

  4. 4.

    https://www.bing.com/new?setlang=en &sid=081BEF962AF260422C13FCAE2BCC615F; last access 22 June 2023.

  5. 5.

    All entries have been conducted or reconfirmed on 30 April 2023 using the release from 23 March 2023; see https://help.openai.com/en/articles/6825453-chatgpt-release-notes.

  6. 6.

    The dataset, code, and models are publicly available at https://github.com/Hello-SimpleAI/chatgpt-comparison-detection; last access 30 April 2023.

  7. 7.

    Question: Can you write code to input a problem instance of the traveling salesman problem to CPLEX?

    Answer: “Yes, I can provide a code snippet in Python to input a TSP instance to CPLEX. Here is an example code that reads a TSP instance from a file in the TSPLIB format, creates a CPLEX model, and solves it: ... ” (ChatGPT).

  8. 8.

    Examples might be the use of INCOTERMS in logistics; see, e.g., https://iccwbo.org/business-solutions/incoterms-rules/incoterms-2020/; last access 30 April 2023.

References

  1. AI HLEG: Ethics Guidelines for Trustworthy AI. European Commission, Brussels (2019). https://digital-strategy.ec.europa.eu/en/library/ethics-guidelines-trustworthy-ai. High-Level Expert Group on Artificial Intelligence. Accessed 22 June 2023

  2. Bang, Y., et al.: A multitask, multilingual, multimodal evaluation of ChatGPT on reasoning, hallucination, and interactivity (2023). https://doi.org/10.48550/arXiv.2302.04023. Available on Arxiv

  3. Berhan, E., Beshah, B., Kitaw, D., Abraham, A.: Stochastic vehicle routing problem: a literature survey. J. Inf. Knowl. Manag. 13(3), 1450022 (2014). https://doi.org/10.1142/S0219649214500221

    Article  Google Scholar 

  4. Castelli, M., Manzoni, L.: Editorial: generative models in artificial intelligence and their applications. Appl. Sci. 12(9), 4127 (2022). https://doi.org/10.3390/app12094127

    Article  Google Scholar 

  5. Du, H., et al.: Chat with ChatGPT on intelligent vehicles: an IEEE TIV perspective. IEEE Trans. Intell. Veh. 8(3), 2020–2026 (2023). https://doi.org/10.1109/TIV.2023.3253281

    Article  Google Scholar 

  6. Frederico, G.F.: ChatGPT in supply chains: initial evidence of applications and potential research agenda. Logistics 7(2), 26 (2023). https://doi.org/10.3390/logistics7020026

    Article  Google Scholar 

  7. Ge, L., Kliewer, N., Nourmohammadzadeh, A., Voß, S., Xie, L.: Revisiting the richness of integrated vehicle and crew scheduling. Public Transp. (2022). https://doi.org/10.1007/s12469-022-00292-6

  8. Ge, L., Nourmohammadzadeh, A., Voß, S., Xie, L.: Robust optimization for integrated vehicle and crew scheduling based on uncertainty in the main inputs. In: The Fifth Data Science Meets Optimisation Workshop at IJCAI-2022, Vienna (2022). https://sites.google.com/view/ijcai2022dso/. Accessed 30 Apr 2023

  9. Ge, L., Voß, S., Xie, L.: Robustness and disturbances in public transport. Public Transp. 14, 191–261 (2022). https://doi.org/10.1007/s12469-022-00301-8

    Article  Google Scholar 

  10. Gendreau, M., Laporte, G., Séguin, R.: Stochastic vehicle routing. Eur. J. Oper. Res. 88, 3–12 (1996). https://doi.org/10.1016/0377-2217(95)00050-X

    Article  Google Scholar 

  11. Golden, B., Raghavan, S., Wasil, E. (eds.): The Vehicle Routing Problem: Latest Advances and New Challenges. Springer, New York (2008). https://doi.org/10.1007/978-0-387-77778-8

    Book  Google Scholar 

  12. Golden, B., Wang, X., Wasil, E.: The Evolution of the Vehicle Routing Problem. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-18716-2

    Book  Google Scholar 

  13. Guo, B., et al.: How close is ChatGPT to human experts? Comparison corpus, evaluation, and detection (2023). https://doi.org/10.48550/arXiv.2301.07597. Available on Arxiv

  14. Haman, M., Školník, M.: Using ChatGPT to conduct a literature review. Account. Res. 1–3 (2023). https://doi.org/10.1080/08989621.2023.2185514

  15. Heilig, L., Lalla-Ruiz, E., Voß, S.: Digital transformation in maritime ports: analysis and a game theoretic framework. NETNOMICS 18, 227–254 (2017). https://doi.org/10.1007/s11066-017-9122-x

    Article  Google Scholar 

  16. Kasneci, E., et al.: ChatGPT for good? On opportunities and challenges of large language models for education. Learn. Individ. Differ. 103, 102274 (2023). https://doi.org/10.1016/j.lindif.2023.102274

    Article  Google Scholar 

  17. Kim, J., Lee, J.: How does ChatGPT introduce transport problems and solutions in North America? Findings (2023). https://doi.org/10.32866/001c.72634. Entry 72634

  18. Konstantakopoulos, G., Gayialis, S., Kechagias, E.: Vehicle routing problem and related algorithms for logistics distribution: a literature review and classification. Oper. Res. Int. J. 22, 2033–2062 (2022). https://doi.org/10.1007/s12351-020-00600-7

    Article  Google Scholar 

  19. Lin, H.Y.: Large-scale artificial intelligence models. Computer 55(5), 76–80 (2022). https://doi.org/10.1109/MC.2022.3151419

    Article  Google Scholar 

  20. McGee, R.W.: How would American history be different if LBJ had lost the 1948 election? A ChatGPT essay (2023). https://doi.org/10.2139/ssrn.4413418. Available at SSRN

  21. Mesquita, M., Moz, M., Paias, A., Pato, M.: A decomposition approach for the integrated vehicle-crew-roster problem with days-off pattern. Eur. J. Oper. Res. 229, 318–331 (2013). https://doi.org/10.1016/j.ejor.2013.02.055

    Article  Google Scholar 

  22. Minoux, M.: Robust linear programming with right-hand-side uncertainty, duality and applications. In: Floudas, C., Pardalos, P. (eds.) Encyclopedia of Optimization, pp. 3317–3327. Springer, Boston (2008). https://doi.org/10.1007/978-0-387-74759-0_569

    Chapter  Google Scholar 

  23. Minoux, M.: Two-stage robust LP with ellipsoidal right-hand side uncertainty is NP-hard. Optim. Lett. 6(7), 1463–1475 (2012). https://doi.org/10.1007/s11590-011-0341-z

    Article  Google Scholar 

  24. Möller, P. (ed.): ChatGPT and the Like: Artificial Intelligence in Logistics. DHL (2023). https://dhl-freight-connections.com/en/trends/chatgpt-and-the-like-artificial-intelligence-in-logistics/. Accessed 10 May 2023

  25. Mollick, E.R., Mollick, L.: Using AI to implement effective teaching strategies in classrooms: five strategies, including prompts (2023). https://doi.org/10.2139/ssrn.4391243. Available at SSRN

  26. Neugebauer, J., Heilig, L., Voß, S.: Digital twins in seaports: current and future applications. In: Daduna, J., et al. (eds.) ICCL 2023. LNCS, vol. 14239, pp. 202–218. Springer, Cham (2023)

    Google Scholar 

  27. Nourmohammadzadeh, A., Voß, S.: An effective matheuristic approach for robust bus driver rostering with uncertain daily working hours. In: Daduna, J., et al. (eds.) ICCL 2023. LNCS, vol. 14239, pp. xx–yy. Springer, Cham (2023)

    Google Scholar 

  28. O’Leary, D.E.: An analysis of three chatbots: BlenderBot, ChatGPT and LaMDA. Intell. Syst. Account. Finance Manag. 30(1), 41–54 (2023). https://doi.org/10.1002/isaf.1531

    Article  Google Scholar 

  29. Otero, I., Salgado, J.F., Moscoso, S.: Cognitive reflection, cognitive intelligence, and cognitive abilities: a meta-analysis. Intelligence 90, 101614 (2022). https://doi.org/10.1016/j.intell.2021.101614

    Article  Google Scholar 

  30. Ouorou, A.: Robust models for linear programming with uncertain right hand side. Networks 68(3), 200–211 (2016). https://doi.org/10.1002/net.21693

    Article  Google Scholar 

  31. Oyola, J., Arntzen, H., Woodruff, D.L.: The stochastic vehicle routing problem, a literature review, part II: solution methods. EURO J. Transp. Logist. 6(4), 349–388 (2017). https://doi.org/10.1007/s13676-016-0099-7

    Article  Google Scholar 

  32. Oyola, J., Arntzen, H., Woodruff, D.L.: The stochastic vehicle routing problem, a literature review, part I: models. EURO J. Transp. Logist. 7(3), 193–221 (2018). https://doi.org/10.1007/s13676-016-0100-5

    Article  Google Scholar 

  33. Özaltın, O.Y., Prokopyev, O.A., Schaefer, A.J.: The bilevel knapsack problem with stochastic right-hand sides. Oper. Res. Lett. 38(4), 328–333 (2010). https://doi.org/10.1016/j.orl.2010.04.005

    Article  Google Scholar 

  34. Ramamonjison, R., et al.: NL4Opt competition: formulating optimization problems based on their natural language descriptions (2023). https://doi.org/10.48550/arXiv.2303.08233. Available on Arxiv

  35. Ritzinger, U., Puchinger, J., Hartl, R.F.: A survey on dynamic and stochastic vehicle routing problems. Int. J. Prod. Res. 54, 215–231 (2016). https://doi.org/10.1080/00207543.2015.1043403

    Article  Google Scholar 

  36. Sar, K., Ghadimi, P.: A systematic literature review of the vehicle routing problem in reverse logistics operations. Comput. Ind. Eng. 177, 109011 (2023). https://doi.org/10.1016/j.cie.2023.109011

    Article  Google Scholar 

  37. Savelsbergh, M., Ulmer, M.: Challenges and opportunities in crowdsourced delivery planning and operations. 4OR 20, 1–21 (2022). https://doi.org/10.1007/s10288-021-00500-2

    Article  Google Scholar 

  38. Shi, Q., Yang, W., Yang, Z.M., Zhao, Q.C.: Relief materials vehicles planning in natural disasters. IEEE/CAA J. Automatica Sin. 5(2), 595–601 (2018). https://doi.org/10.1109/JAS.2017.7510850

    Article  Google Scholar 

  39. Soeffker, N., Ulmer, M.W., Mattfeld, D.C.: Stochastic dynamic vehicle routing in the light of prescriptive analytics: a review. Eur. J. Oper. Res. 298, 801–820 (2022). https://doi.org/10.1016/j.ejor.2021.07.014

    Article  Google Scholar 

  40. Solis, T.: Die ChatGPT-Richtlinien der 100 größten deutschen Universitäten (2023). https://www.scribbr.de/ki-tools-nutzen/chatgpt-universitaere-richtlinien/. Accessed 22 June 2023

  41. Stokel-Walker, C., Van Noorden, R.: The promise and peril of generative AI. Nature 614, 214–216 (2023). https://doi.org/10.1038/d41586-023-00340-6

    Article  Google Scholar 

  42. Sun, Y., et al.: ERNIE: enhanced representation through knowledge integration (2019). https://doi.org/10.48550/arXiv.1904.09223. Available on Arxiv

  43. Toth, P., Vigo, D.: Vehicle Routing: Problems, Methods, and Applications, 2nd edn. SIAM, Philadelphia (2014)

    Book  Google Scholar 

  44. Voß, S., Gutenschwager, K.: Informationsmanagement. Springer, Berlin (2001). https://doi.org/10.1007/978-3-642-56878-7

    Book  Google Scholar 

  45. Voß, S.: Bus bunching and bus bridging: what can we learn from generative AI tools like ChatGPT? Sustainability 15(12, article #9625) (2023). https://doi.org/10.3390/su15129625

  46. Wang, D., Lu, C.T., Fu, Y.: Towards automated urban planning: when generative and ChatGPT-like AI meets urban planning (2023). https://doi.org/10.48550/arXiv.2304.03892. Available on Arxiv

  47. Wang, F.Y., Yang, J., Wang, X., Li, J., Han, Q.L.: Chat with ChatGPT on Industry 5.0: learning and decision-making for intelligent industries. IEEE/CAA J. Automatica Sin. 10(4), 831–834 (2023). https://doi.org/10.1109/JAS.2023.123552

    Article  Google Scholar 

  48. Winston, P.H.: Artificial Intelligence. Addison-Wesley, Boston (1992). (1st edn. in 1977)

    Google Scholar 

  49. Xiong, C., Chen, X., He, X., Lin, X., Zhang, L.: Agent-based en-route diversion: dynamic behavioral responses and network performance represented by macroscopic fundamental diagrams. Transp. Res. Part C Emerg. Technol. 64, 148–163 (2016). https://doi.org/10.1016/j.trc.2015.04.008

    Article  Google Scholar 

  50. Yang, Z.: The bearable mediocrity of Baidu’s ChatGPT competitor. MIT Technology Review (2023). https://www.technologyreview.com/2023/03/22/1070154/baidu-ernie-bot-chatgpt-reputation/. Accessed 10 May 2023

  51. Zhang, C., et al.: One small step for generative AI, one giant leap for AGI: a complete survey on ChatGPT in AIGC era (2023). https://doi.org/10.48550/arXiv.2304.06488. Available on Arxiv

  52. Zheng, O., Abdel-Aty, M., Wang, D., Wang, Z., Ding, S.: ChatGPT is on the horizon: could a large language model be all we need for intelligent transportation? (2023). https://doi.org/10.48550/arXiv.2303.05382. Available on Arxiv

  53. Zhu, J.J., Jiang, J., Yang, M., Ren, Z.J.: ChatGPT and environmental research. Environ. Sci. Technol. (2023). https://doi.org/10.1021/acs.est.3c01818

Download references

Author information

Authors and Affiliations

  1. Institute of Information Systems, University of Hamburg, Von-Melle-Park 5, 20146, Hamburg, Germany

    Stefan Voß

Authors
  1. Stefan Voß
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Stefan Voß .

Editor information

Editors and Affiliations

  1. Hochschule für Wirtschaft und Recht Berlin, Berlin, Germany

    Joachim R. Daduna

  2. Deutsches Zentrum für Luft- und Raumfahrt (DLR), Berlin, Germany

    Gernot Liedtke

  3. Deutsches Zentrum für Luft- und Raumfahrt (DLR), Berlin, Germany

    Xiaoning Shi

  4. University of Hamburg, Hamburg, Germany

    Stefan Voß

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Voß, S. (2023). Successfully Using ChatGPT in Logistics: Are We There Yet?. In: Daduna, J.R., Liedtke, G., Shi, X., Voß, S. (eds) Computational Logistics. ICCL 2023. Lecture Notes in Computer Science, vol 14239. Springer, Cham. https://doi.org/10.1007/978-3-031-43612-3_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-43612-3_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-43611-6

  • Online ISBN: 978-3-031-43612-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics