ISSN (Online): 2321-3418
server-injected
Engineering and Computer Science
Open Access

AI-Driven Fleet Optimization for Supply-Chain Resilience and Logistics Efficiency

DOI: 10.18535/ijsrm/v13i05.ec07· Pages: 2208-2223· Vol. 13, No. 05, (2025)· Published: May 30, 2025
PDF
Views: 6 PDF downloads: 1

Abstract

Abstract AI-driven fleet optimization for supply-chain resilience and logistics efficiency is a field that uses machine learning, optimization algorithms, and data integration to improve routing, scheduling, and asset utilization across freight, parcel, and warehouse networks. By analyzing real-time and historical data from vehicles, sensors, traffic, and business systems, these solutions aim to forecast demand, select carriers, dynamically re-plan routes, and reduce costs while boosting on-time delivery and visibility. Proponents argue that AI can address the limitations of traditional ERP and forecasting models in handling complex, heterogeneous data, contributing to more resilient and efficient supply chains (ABI Research, 2026; arXiv, 2026; SupplyChainBrain, n.d.). At its core, the approach combines modular AI and operations research methods with data architectures such as knowledge graphs and conversational interfaces to enable bidirectional communication between fleet managers and warehouse operators. Key components commonly described include an optimization engine, a knowledge graph for semantic data exchange, and AI-driven decision-support interfaces (including retrieval-augmented generation and mixed-reality visualization) that support real-time planning and execution across cloud and on-premise deployments (arXiv, 2026; Operations Research Stack Exchange, n.d.). This framework is designed to integrate with core systems like TMS, WMS, and ERP, and is often implemented as containerized microservices to support scalable, end-to-end workflows from forecasting to execution (arXiv, 2026). The field has moved from theory to real-world deployments and demonstrations. Large players have applied AI-enabled routing and autonomous decision-support to reduce miles driven, lower fuel usage, and increase capacity in dense and dispersed networks. Notable examples include corporate route optimization programs and pilots in parcel and freight operations, as well as supplier and carrier collaboration platforms that illustrate tangible efficiency, resilience, and sustainability gains under dynamic conditions (AQE Digital, n.d.; Felt, n.d.; LinkedIn, n.d.-d; Nextmv, n.d.; Stack Overflow, n.d.). Industry analyses and case studies emphasize that the value of AI-driven fleet optimization grows when paired with integrated risk monitoring, digital twins, and end-to-end visibility across dispatch, tracking, and fulfillment (Nextmv, n.d.; Operations Research Stack Exchange, n.d.). Prominent contemporary debates and challenges center on data governance, regulatory compliance, and the ethics of AI-driven decision-making. Critics emphasize the need for data quality, interoperability, transparency, and bias mitigation, along with governance and due diligence when selecting vendors and integrating with legacy systems. Regulators are increasingly focusing on safety, traceability, privacy, and explainability, prompting emphasis on auditable records, data protection (GDPR/CCPA), and responsible deployment practices as AI-enabled logistics platforms mature (Geotab, n.d.-a; Medium, n.d.; Operations Research Stack Exchange, n.d.). Proponents counter that careful governance and modular architectures can unlock substantial resilience and efficiency benefits while maintaining human oversight and accountability (Operations Research Stack Exchange, n.d.).

Keywords

AI-Driven Fleet OptimizationSupply-Chain Resilience and Logistics Efficiency

References

  1. ABI Research. (2026). Supply chain disruptions 2026: How to build resilience with AI and. https://www.abiresearch.com/blog/supply-chain-disruptions-2026-how-to-build-resilience-with-ai-and-automationGoogle Scholar ↗
  2. AIMultiple. (n.d.). Top 15 logistics AI use cases & examples. https://aimultiple.com/logistics-aiGoogle Scholar ↗
  3. Aptean. (n.d.). AI route optimization: Logistics levels up. https://www.aptean.com/en-US/resources/industry-insights/blog/ai-route-optimization-capabilitiesGoogle Scholar ↗
  4. AQE Digital. (n.d.). AI-powered fleet management solution case study. https://www.aqedigital.com/case-studies/ai-analytics-for-fleet-management/Google Scholar ↗
  5. Artech Digital. (n.d.). Real-time route optimization with AI. https://www.artech-digital.com/blog/real-time-route-optimization-with-aiGoogle Scholar ↗
  6. arXiv. (2025). Towards a better approach to the vehicle routing problem. https://arxiv.org/html/2506.23028v1Google Scholar ↗
  7. arXiv. (2026). Vehicle routing problem meets large language models: An overview and. https://arxiv.org/html/2607.00604v1Google Scholar ↗
  8. Autofleet. (n.d.-a). Best 8 route optimization software for fleet operators. https://autofleet.io/blog/best-route-optimization-software-for-fleet-operationsGoogle Scholar ↗
  9. Autofleet. (n.d.-b). The AI revolution in fleet management optimization. https://autofleet.io/blog/ai-for-fleet-management-optimizing-fleet-operationsGoogle Scholar ↗
  10. BluEnt. (n.d.). AI for supply chain resilience & optimization. https://www.bluent.com/blog/ai-in-supply-chainGoogle Scholar ↗
  11. BSR. (n.d.). ORION technology adoption at UPS | case studies. https://www.bsr.org/en/case-studies/center-for-technology-and-sustainability-orion-technology-upsGoogle Scholar ↗
  12. C3 AI. (n.d.). AI supply chain resilience and growth: A guide. https://c3.ai/blog/the-power-of-ai-in-supply-chain-management-for-increased-resilience-and-growthGoogle Scholar ↗
  13. DHL. (n.d.). The future of AI in logistics and last-mile delivery in australia. https://www.dhl.com/discover/en-au/ship-with-dhl/start-shipping/benefits-of-artificial-intelligence-in-last-mile-deliveryGoogle Scholar ↗
  14. DigitalDefynd. (2026). 10 ways DHL is using AI [Case study] [2026]. https://digitaldefynd.com/IQ/dhl-using-ai-case-study/Google Scholar ↗
  15. Eide Bailly. (2025). Optimizing supply chains: Efficiency, risk reduction, and reshoring for. https://www.eidebailly.com/insights/articles/2025/3/ai-enabled-data-and-supply-chain-resiliencyGoogle Scholar ↗
  16. Eindhoven University of Technology. (n.d.-a). Dynamic and stochastic vehicle routing problems: A reinforcement. https://research.tue.nl/en/publications/dynamic-and-stochastic-vehicle-routing-problems-a-reinforcement-l/Google Scholar ↗
  17. Eindhoven University of Technology. (n.d.-b). Vehicle routing problem with stochastic travel times including soft. https://research.tue.nl/en/publications/vehicle-routing-problem-with-stochastic-travel-times-including-so-2/Google Scholar ↗
  18. FarEye. (n.d.). How does dynamic route planning & optimization enhance efficiency? https://fareye.com/resources/blogs/dynamic-route-optimization-and-planningGoogle Scholar ↗
  19. Felt. (n.d.). Fleet optimization: Definition, metrics, and key strategies. https://felt.com/blog/fleet-optimizationGoogle Scholar ↗
  20. Geotab. (n.d.-a). AI in fleet management: How to improve efficiency & reduce costs. https://www.geotab.com/blog/ai-fleet-management/Google Scholar ↗
  21. Geotab. (n.d.-b). Fleet routing software for optimal vehicle dispatch. https://www.geotab.com/fleet-management-solutions/routing-dispatching/Google Scholar ↗
  22. Gurobi. (n.d.). Vehicle routing problems FAQ: Practical route optimization. https://www.gurobi.com/resources/faq/vehicle-routing-problems-faq-practical-route-optimizationGoogle Scholar ↗
  23. HEC Montreal. (2024). The stochastic production routing problem with adaptive. https://chairelogistique.hec.ca/wp-content/uploads/2024/09/SPRP-SLC.pdfGoogle Scholar ↗
  24. INFORMS. (n.d.). Optimizing delivery routes. https://www.informs.org/Impact/O.R.-Analytics-Success-Stories/Optimizing-Delivery-RoutesGoogle Scholar ↗
  25. IVADO. (n.d.). Combining machine learning and optimization to manage uncertainty. https://ivado.ca/combining-machine-learning-and-optimization-to-manage-uncertainty-in-supply-chains/Google Scholar ↗
  26. Kellton. (n.d.). AI in transportation: Predictive logistics & autonomous fleet. https://www.kellton.com/kellton-tech-blog/ai-in-transportation-predictive-logistics-autonomous-fleet-managementGoogle Scholar ↗
  27. LinkedIn. (n.d.-a). AI in inventory planning: Separating value from hype | matt stekier posted. https://www.linkedin.com/posts/matt-stekier-881177a_why-aidriven-inventory-optimization-frameworks-activity-7482773330341732352-TmxgGoogle Scholar ↗
  28. LinkedIn. (n.d.-b). Fleet management optimization. https://www.linkedin.com/top-content/supply-chain-management/logistics-network-design/fleet-management-optimization/Google Scholar ↗
  29. LinkedIn. (n.d.-c). How AI is transforming logistics with DHL and delivery hero. https://www.linkedin.com/posts/andrii-aleksieiev-_the-smart-road-to-efficiency-ai-driven-routing-activity-7384875839102029826-8SJTGoogle Scholar ↗
  30. LinkedIn. (n.d.-d). Robust logistics optimization. https://www.linkedin.com/top-content/supply-chain-management/supply-chain-resilience/robust-logistics-optimization/Google Scholar ↗
  31. LinkedIn. (n.d.-e). The complete guide to AI logistics optimization. https://www.linkedin.com/pulse/complete-guide-ai-logistics-optimization-finlogistics-lljtfGoogle Scholar ↗
  32. Locus. (n.d.). What is vehicle routing: Definition, tools, and strategies. https://locus.sh/blogs/what-is-vehicle-routing/Google Scholar ↗
  33. MDPI. (n.d.-a). A systematic review of uncertainty handling approaches. https://www.mdpi.com/1996-1073/16/13/4983Google Scholar ↗
  34. MDPI. (n.d.-b). A three-stage stochastic model to improve resilience with lateral. https://www.mdpi.com/2079-8954/12/3/73Google Scholar ↗
  35. MDPI. (n.d.-c). Artificial intelligence in logistics optimization with sustainable criteria. https://www.mdpi.com/2071-1050/16/21/9145Google Scholar ↗
  36. Medium. (n.d.). How to solve routing problem with stochastic programming approaches. https://medium.com/eni-digitalks/how-to-solve-routing-problem-with-stochastic-programming-approaches-2440aa8ade1bGoogle Scholar ↗
  37. National Library of Medicine. (n.d.-a). Enhancing last-mile logistics: AI-driven fleet optimization. https://pmc.ncbi.nlm.nih.gov/articles/PMC12074495/Google Scholar ↗
  38. National Library of Medicine. (n.d.-b). How managerial perspectives affect the optimal fleet size and mix model. https://pmc.ncbi.nlm.nih.gov/articles/PMC9652047/Google Scholar ↗
  39. Nature. (2025). Rich vehicle routing optimization based on variable. https://www.nature.com/articles/s41598-025-06946-2Google Scholar ↗
  40. NextBillion.ai. (n.d.). Heterogeneous fleet vehicle routing problem. https://nextbillion.ai/feeds/blog/heterogeneous-fleet-vehicle-routing-problemGoogle Scholar ↗
  41. Nextmv. (n.d.). Getting started with vehicle routing problems (VRPs) — and testing, too! https://www.nextmv.io/videos/getting-started-with-vehicle-routing-problems-vrps-and-testing-tooGoogle Scholar ↗
  42. OpenAIRE. (n.d.). Robust optimization for fleet planning under uncertainty. https://oamonitor.ireland.openaire.eu/national/search/publication?pid=10.1016%2Fs1366-5545(02)00026-1Google Scholar ↗
  43. Operations Research Stack Exchange. (n.d.). CVRP with unconstrained fleet size: Upper bound on optimal fleet size. https://or.stackexchange.com/questions/2619/cvrp-with-unconstrained-fleet-size-upper-bound-on-optimal-fleet-sizeGoogle Scholar ↗
  44. Optimization Online. (2023). Fair stochastic vehicle routing with partial deliveries. https://optimization-online.org/wp-content/uploads/2023/04/Optimization-Online-Fair-stochastic-vehicle-routing-with-partial-deliveries-1.pdfGoogle Scholar ↗
  45. Oxmaint. (n.d.). AI-driven fleet management: The future of fleet optimization. https://oxmaint.com/industries/fleet-management/ai-driven-fleet-management-future-optimizationGoogle Scholar ↗
  46. PRISM Model Checker. (n.d.). Vehicle dispatch in on-demand ride-sharing with stochastic travel times. https://www.prismmodelchecker.org/papers/iros21.pdfGoogle Scholar ↗
  47. RELEX Solutions. (n.d.). Supply chain scenario planning guide. https://www.relexsolutions.com/resources/supply-chain-scenario-planning/Google Scholar ↗
  48. ResearchGate. (n.d.-a). Application of artificial intelligence in logistics 4.0: DHL case study analysis. https://www.researchgate.net/publication/385039143_Application_of_Artificial_intelligence_in_Logistics_40_DHL_case_study_analysisGoogle Scholar ↗
  49. ResearchGate. (n.d.-b). Exploring AI-driven supply chain automation to enhance global. https://www.researchgate.net/publication/395514209_Exploring_AI-driven_supply_chain_automation_to_enhance_global_logistics_reduce_operational_costs_and_ensure_resilient_business_continuityGoogle Scholar ↗
  50. SafetyTrack. (n.d.). How AI fleet optimization tools transform your operations. https://www.safetytrack.com/blog/how-ai-fleet-optimization-tools-transform-your-operations/Google Scholar ↗
  51. ScienceDirect. (n.d.-a). A two-stage robust optimization approach for the mobile. https://www.sciencedirect.com/science/article/abs/pii/S0305054815002178Google Scholar ↗
  52. ScienceDirect. (n.d.-b). The probabilistic vehicle routing problem with service guarantees. https://www.sciencedirect.com/science/article/abs/pii/S1366554517307494Google Scholar ↗
  53. ScienceDirect. (n.d.-c). The stochastic vehicle routing problem, a literature review, part i. https://www.sciencedirect.com/science/article/pii/S2192437620300649Google Scholar ↗
  54. ScienceDirect. (n.d.-d). The vehicle routing problem with hard time windows and stochastic service. https://www.sciencedirect.com/science/article/pii/S2192437620300650Google Scholar ↗
  55. ShippyPro. (n.d.). Top 8 use cases of artificial intelligence in logistics. https://www.shippypro.com/blog/en/ai-logistics-use-casesGoogle Scholar ↗
  56. Stack Overflow. (n.d.). Solving vehicle routing for cost optimization. https://stackoverflow.com/questions/37679375/solving-vehicle-routing-for-cost-optimizationGoogle Scholar ↗
  57. SupplyChainBrain. (n.d.). Revolutionizing supply chain resilience with AI-driven lead time. https://www.supplychainbrain.com/articles/42689-revolutionizing-supply-chain-resilience-with-ai-driven-lead-time-predictionGoogle Scholar ↗
  58. Taylor & Francis. (n.d.). Adjustable robust optimization for integrated fleet sizing and vehicle. https://www.tandfonline.com/doi/abs/10.1080/21681015.2024.2387820DOI ↗Google Scholar ↗
  59. Technical University of Munich. (n.d.). Contextual stochastic vehicle routing with time windows. https://www.ot.mgt.tum.de/log/news/article/new-publication-contextual-stochastic-vehicle-routing-with-time-windows/Google Scholar ↗
  60. The Morning Paper. (2019). A survey on dynamic and stochastic vehicle routing problems. https://blog.acolyer.org/2019/02/15/a-survey-on-dynamic-and-stochastic-vehicle-routing-problems/Google Scholar ↗
  61. University of Virginia. (n.d.). Maritime fleet schedule optimization and disruption of ... - libra etd. https://libraetd.lib.virginia.edu/public_view/oid-d3atnqg5smgc714ms3og/download?file=1_Jabs_Nick_2025_MS.pdfGoogle Scholar ↗
  62. Weise. (2019). ORION: Route optimization at UPS. https://joachimweise.github.io/post/2019-11-30-ups-orion/Google Scholar ↗
Author details
Bekzod Sharipov
👤 View Profile →🔗 Is this you? Claim this publication