110064 - ARTIFICIAL INTELLIGENCE APPLIED TO LOGISTICS

Subject type: Optional

Coordinator: Valeria Bernardo

Trimester: First term

Credits: 5

Academic year: 2026

Teaching course: 4

• Spanish

Skills that are worked on

• Students will develop an understanding of the fundamental concepts of artificial intelligence, including its types, associated technologies and areas of application. They will be trained to identify and understand the underlying principles of techniques such as machine learning, neural networks and natural language processing. Through case studies and practical exercises, students will be able to recognize how these technologies can be applied to various sectors, acquiring a critical view on the advantages, limitations and ethical challenges of AI in general and in the field of logistics in particular.
• Students will be able to identify the aspects in which AI can be applied to logistics to optimize supply chain management, route planning, demand forecasting and automation of logistics processes. They will be provided with practical knowledge to use AI algorithms in solving complex logistics problems, which will allow them to improve operational efficiency and make informed decisions in a dynamic and globalized environment. In addition, they will be trained to evaluate the benefits and potential risks associated with the integration of AI in general and in logistics operations in particular.

Learning outcomes

• Learn what AI is, its types, learning methods and applications in different fields and in logistics.

Working methodology

1.- Structure of the theoretical and practical sessions

1.1.- Microseminars

With the aim of promoting progressive and applied learning, the theoretical sessions of the subject will be structured into thematic blocks or clearly differentiated parts, divided into micro-seminars in which a set of key concepts related to artificial intelligence will be addressed, as well as a practical part with examples of its application both in general and in the field of logistics.

The practical sessions, aimed at consolidating the acquired knowledge, will be based on dynamic activities such as debates, solving challenges, analyzing real cases or working with generative AI tools. These sessions are designed to encourage active participation, critical thinking and the connection between theoretical content and its application in real logistics contexts.

This structure aims not only to facilitate the assimilation of the contents, but also to arouse the interest of students and promote a reflective and creative attitude towards the challenges posed by artificial intelligence in current and future logistics.

1.2.- Presentations

Multimedia formats that support face-to-face classes.

1.3.- Practical sessions after each thematic block

Discussions and forums: face-to-face conversations after each thematic block. Participation, content of contributions and correct compliance with the rules of use will be taken into account.

Case study: dynamic that starts from the study of a case. The objective is to contextualize the student in a specific situation. The teacher can propose different activities, both individual and in groups, among the students.

Role-playing games: Simulation dynamics in which each student assumes a role specified by the teacher. As a "role", they will have access to specific information and must "play", following the rules of the game, to resolve or experience the reference situation of the dynamics.

2.- Independent or group learning

Exercise solution: Non-face-to-face activity dedicated to solving practical exercises based on the data provided by the teacher.

Critical reading of articles: Students start from a working hypothesis that they will develop following the phases of the research methodology, which includes critical reading of articles.

Tutorials: face-to-face and non-face-to-face. In the latter, the student will have access to telematic resources, such as email and the resources of the ESCSET intranet.

Course work: Activity in which each student works on a specific topic. In the final phase, they make a presentation and a short debate is opened.

The classroom (physical or virtual) is a safe space, free from sexist, racist, homophobic, transphobic and discriminatory attitudes, both towards students and teachers. We trust that, among all of us, we can create a safe space where we can make mistakes and learn without having to suffer the prejudices of others.

Topic 1: What is AI / Pillars / Types / Brief history

Topic 2: AI capabilities and limitations

Topic 3: Current and future applications of AI

Topic 4: AI applied to the business

Topic 5: AI applied to logistics

Each section will present examples of the use of AI in general and in the field of logistics in particular. This will then lead to the practical part, structured in the form of micro-seminars.

Learning activities

Individual work of the student's choice related to the subject

As part of the continuous assessment, the student must carry out individual work on a topic of their choice, as long as it is linked to the contents of the subject and allows for in-depth study of some aspect of artificial intelligence applied to logistics.

To ensure the coherence of the work and its viability, each student must first present a proposal to the professor, who will assess it and, if necessary, give his/her approval. This step is not intended to limit creativity, but to accompany the student in choosing the most appropriate approach, ensuring that the topic is relevant and that the subsequent development is enriching.

Originality, critical analysis and the ability to establish connections between theoretical content and real or potential situations in the logistics field will be particularly valued.

To carry out this work, the student must use at least two generative AI tools: one as support for content generation and another for image generation. The work must comply with TCM regulations.

Evaluation system

1.- Continuous evaluation

The following percentages apply:

In the event that the final exam grade is lower than 5, or that the weighted final grade (work + exam) does not reach 5, the student may opt for retake, provided that they have appeared for the regular final exam.

2.- Recovery

The following percentages apply:

Any form of academic fraud will be sanctioned in accordance with the center's assessment regulations. If signs of fraud are detected, including the improper use of generative artificial intelligence tools, the subject's teaching staff may call the student for an individual interview with the aim of verifying their authorship.

Martínez de Carvajal Hedrich, Ernesto. AI Applied to Logistics. Barcelona: EMCH TechBooks, 2024.

Martínez de Carvajal Hedrich, Ernesto. Talking to an AI. Barcelona: EMCH TechBooks, 2023.

McKinsey & Company. (2024). Using digital twins to unlock supply chain growth. McKinsey & Company. https://www.mckinsey.com

Wamba, SF, Dubey, R., Gunasekaran, A., & Akter, S. (2024). Generative artificial intelligence in supply chain and operations: Opportunities and challenges. Annals of Operations Research. https://doi.org/10.1007/s10479-024-06156-2