cs.AIOct 1, 2026

Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics

Authors: Antonio Emanuele Cinà, Giovanni Scodeller, Cecilia Caterina Pasquale, Silvia Siri, Davide Anguita, Fabio Roli, Simona Sacone, Luca Oneto

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

The rapid evolution of Intelligent Transportation Systems and Logistics (ITS&L) has become a cornerstone of the modern social economy, relying heavily on the integration of Data, Artificial Intelligence (AI), and, more specifically, Machine Learning (ML). This paper provides a comprehensive review of Trustworthy Data and Machine Learning Operations (DataOps and MLOps) in the ITS&L domain, underscoring their importance in improving efficiency, reliability, and decision-making precision within transportation and logistics services. We begin by identifying gaps in current literature, offering clear context for our contribution. Subsequently, we explore the complexities of DataOps and MLOps, discussing their necessity, key components, available tools, practical insights, and case studies relevant to ITS&L. Additionally, we address the critical issue of Trustworthiness in AI applications, examining methods and tools designed to strengthen confidence in AI systems - especially in real-world ITS&L scenarios. The paper concludes with a discussion of persisting challenges and future prospects in this rapidly advancing field, aiming to serve as a vital resource for researchers, industry practitioners, and policy makers. Overall, this work not only establishes a foundational understanding of DataOps and MLOps in ITS&L but also charts a path for further research and innovation in developing more efficient, sustainable, and trustworthy intelligent transportation and logistics systems.

Figures & tables

Figure 1: DataOps and MLOps in ITS&L. Heterogeneous data sources are governed through the DataOps lifecycle and subsequently support the MLOps lifecycle for model development, deployment, monitoring, and updating. The resulting AI-enabled services operate across the main ITS&L application domains, while TAI provides a governance layer grounded in robustness, explainability, fairness, privacy, and sustainability.
Ref.YearITS&LDataOpsMLOpsTAIKeywords
TrustworthyAI Surveys
[ 49 ]2018    Adversarial machine learning, Evasion attacks, Poisoning attacks, Adversarial examples, Secure learning, Deep learning
[ 50 ]2021    Trustworthy AI, robustness, generalization, explainability, transparency, reproducibility, fairness, privacy protection, accountability
[ 28 ]2021    Machine learning, privacy, deep learning, differential privacy
[ 51 ]2022    Learning on graphs, Graph neural networks, Kernels for graphs, Trustworthy machine learning, Fairness, Privacy, Robustness, Explainability, Learning automatically Learning with guarantees
[ 26 ]2023    Poisoning attacks, backdoor attacks, Machine learning, Computer vision, Computer security
TABLE I: Meta-review of existing surveys in the ITS&L, DataOps , MLOps , and TAI research fields.
Figure 2: DataOps abstract lifecycle.
ToolSourceDataOps phase(s)ProcessingOn-premiseScalabilityLimitation
Open-source – core data processing tools
Apache KafkaOpen-sourceIngestion, MonitoringStream High throughput and low latency for large-scale streamsRequires expertise to configure, operate, and maintain distributed streaming clusters
Apache HDFSOpen-sourceStorage– Horizontal scalability through data replication and node additionPrimarily designed for storage and batch-oriented workloads, requiring complementary tools for real-time analytics
Apache SparkOpen-sourceProcessingBatch Distributed in-memory processing across multiple nodes, reducing disk accessCluster configuration and performance tuning can be complex in production environments
Apache FlinkOpen-sourceProcessingStream Reduces storage overhead by processing continuous streamsOperationally more complex than batch-oriented frameworks and often requires strong stream-processing expertise
Open-source – Ops tools, from release to feedback
TABLE II: Comparison of representative DataOps tools.
Figure 3: MLOps abstract lifecycle.
ToolMLOps phase(s)AutoMLOn-premiseScalabilityLimitation
Open-source – core ML pipeline tools
MetaflowData engineering, training, validation, deployment× On-demand cloud integration for large-scale workloadsDoes not cover the full MLOps pipeline; monitoring and feedback stages require additional tools
ZenMLEnd-to-end× Via third-party integrations with cloud and on-premise servicesRelies on external tools, such as MLflow, Weights and Biases, and BentoML, to cover several pipeline stages, adding integration overhead
BentoMLRelease, packaging, deployment, serving, monitoring support× Docker, Kubernetes, and cloud services via BentoctlFocuses mainly on release, deployment, and serving rather than on the full training and validation lifecycle
KubeflowEnd-to-end  Distributed execution across Kubernetes clustersTightly coupled to Kubernetes infrastructure, requiring significant DevOps expertise to deploy and maintain
ApolloData engineering, validation, deployment, monitoring× Simulation-based testing environments for vehicle control applicationsNot designed for general ML workflows domains beyond vehicle control
TABLE III: Comparison of representative MLOps tools.
AreasRef(s)# Ref(s)DataOpsMLOpsTAI
Sustain.Robust.XAIFairnessPrivacy
Vehicle Control[ 122 , 180 , 178 , 179 , 180 , 181 , 182 , 183 , 184 , 185 , 186 , 187 ]12       
[ 280 , 281 , 282 ]3       
[ 493 , 494 , 495 , 496 , 497 , 498 , 499 , 500 , 501 ]9       
[ 489 , 490 , 491 , 502 , 492 ]5       
[ 484 , 486 , 487 , 488 ]4       
TABLE IV: Case studies summary for DataOps , MLOps , and TAI .
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15

Explore similar work

CardsList
May 31, 2026cs.AI

Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support

Transportation systems management and operations (TSMO) increasingly depends on timely interpretation of heterogeneous data, from various sensor streams, incident reports, traveler feedback, and visual observations. Large language models (LLMs), including emerging multi-modal large language models (MM-LLMs), provide a new mechanism for integrating these structured and unstructured inputs into operator-facing decision support. This survey paper reviews LLM- and MM-LLM-based applications in TSMO across three domains: transportation operations & services (supply), mobility & fleet services (demand), and data, modeling & decision support. Using a PRISMA-guided screening process, we synthesize current studies while distinguishing operationally oriented applications from prototype and emerging concepts. We further identify recurring challenges in data heterogeneity, real-time inference, explainability, multi-modal fusion, and governance. Finally, we outline existing gaps and future directions in localized adaptation, edge deployment, benchmarking, and cross-agency collaboration. Overall, LLM-based systems appear most promising as a decision-support layer, with MM-LLMs offering particular value when heterogeneous text, visual, and sensor inputs must be integrated.

Siyan Li, Zehao Wang, Jiachen Li +3

Bourns College of Engineering, Center for Environmental Research and Technology, University of California at Riverside, CA, USA · Bourns College of Engineering, Computer Science and Engineering Department, University of California at Riverside, CA, USA · Bourns College of Engineering, Electrical and Computer Engineering Department, University of California at Riverside, CA, USA

Multimodal Large Language ModelsSoftware Engineering Decision SupportTransportReasoning Skills
AskPDF
Aug 8, 2026cs.AI

Large Multimodal Agents for Intelligent Transportation Systems: Architectures, Evidence, and Deployment Challenges

Large multimodal agents (LMAs) are increasingly proposed for intelligent transportation systems (ITS), but existing studies often conflate multimodality, agency, empirical performance, and deployment readiness. This review provides an auditable evidence map of 42 primary study families released between January 2023 and 3 August 2026 within a corpus of 91 mapped sources. It distinguishes model-level, system-level, and hybrid multimodality and classifies each family by system architecture and action authority. Evidence is assessed independently through functional capability (C0-C3), validation setting (E0-E4), three evidence propositions (P1-P3), and eight methodological-concern domains (Q1-Q8). Transportation semantics (P1) are directly evaluated in 23 families and multidimensional integration (P3) in 24; 19 families directly evaluate both. Evidence reconciliation (P2) remains unresolved because no family demonstrates the complete provenance-challenge-handling-comparison-outcome chain. Fourteen families reach C3, but 13 remain at E2; only one reaches E3 and none reaches E4. Across ITS domains, LMAs are best supported for semantic interpretation, intent translation, evidence organisation, scenario authoring, explanation, and specialist-tool coordination. Numerical forecasting, optimisation, simulation fidelity, hard constraints, low-level control, safety fallback, and final authority should remain with independently verifiable specialist systems or accountable humans. The review therefore supports bounded orchestration rather than replacement and provides a matched comparative evaluation protocol and staged roadmap for accountable deployment. The living evidence repository is available at https://github.com/pangjunbiao/ITS-LMA-Review.

Muhammad Ayub Sabir, Shaohong Zheng, Zhiyu Qu +2

Multimodal AgentsModel-Based Multi-Agent SystemsMulti-Modal Data
AskPDF
Apr 30, 2026cs.CR

A Comparative Analysis of Machine Learning Models for Intrusion Detection in Intelligent Transport Systems

AI-powered edge computing security is moving Intelligent Transportation Systems (ITS) from passive, rule-based protections to proactive, smart, zero-touch, self-sufficient safeguards that neutralize threats in milliseconds. As transportation becomes more connected with edge computing, massive IoT, and advanced 5G for vehicle-to-everything (V2X) connectivity, AI at the edge computing nodes plays a crucial role in protecting against sophisticated threats, enabling URLLC (ultra-low-latency communications) for smart transport, and enhancing infrastructure capabilities and safety. This research applies edge computing to improve latency, bandwidth efficiency, and service responsiveness by moving processing closer to devices, gateways, and users. However, this shift also expands the cyberattack surface because edge nodes are distributed, heterogeneous, and often resource-constrained. The paper proposes a trust-aware federated hybrid intrusion detection framework in which a random forest, a decision tree, and a linear SVM network learn complementary traffic representations at each edge site, while a server performs trust-aware aggregation of local model updates.

Zawad Yalmie Sazid, Robert Abbas, Sasa Maric

Victoria University, Sydney, Australia · University of New South Wales College, Sydney, Australia

Edge DevicesIntrusion DetectionIntelligent TransportationMobilityComparison
AskPDF