106323 - ARTIFICIAL INTELLIGENCE

Subject type: Mandatory

Coordinator: Juan José Pons López

Trimester: Second term

Credits: 4

Academic year: 2025

Teaching course: 3

• Catalan

Documentation mostly in English. Language used in class: Catalan. Exercises and tests in Catalan and / or English. 

This subject aims to introduce degree students to the field of artificial intelligence, and specifically to computational behaviour, showing them the application of some of its techniques in the construction of video games. Issues such as movement-based behaviors, including wayfinding, and a small range of decision-making mechanisms of a reactive nature are seen. The theoretical aspects are worked on, in an expository way, and their subsequent practical application, aimed at the resolution, often guided, of small problems. The class sessions combine both aspects in order to achieve a good balance between them. The practices (compulsory) and exercises in class and at home make up the evaluation model of the subject. 

This subject should be taken once the entire first year and the "programming in interpreted languages" subject of the second year have been passed. It would also be advisable to have passed the subject "Development of 2D games".

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

Topic 1. Introduction. AI and AI for games. Computational behaviors

Topic 2. Motion control: "Steering behaviors"

2.1 Basic and derived behaviors: seek, arrive, wander, velocity matching,...

2.2 Combination of behaviors. Flocking

Topic 3. Pathfinding: "Pathfinding"

3.1 Representation of space: graphs

3.2 The A star algorithm

Item 4. Decision making

4.1 State machines

4.2 Behavioral trees

The grade of each student will be calculated following the following percentages:

A (1,2,3). Laboratory practices / group work: 50% (1/3 50% each)

A4. Final Exam: 50%

Final Note = A (1,2,3) · 0.5 + A4 · 0.5

Considerations:

- A(1, 2, 3) are considered a single activity composed of several sections that have deliveries distributed during the quarter. 

- A4> = 5 is required to pass the subject. If this grade does not reach 5 then she herself will be the final grade. 

- An activity not delivered or delivered late and without justification (court summons or medical matter) counts as a 0.

- In general, TecnoCampus establishes: Any form of academic fraud will be sanctioned in accordance with the center's evaluation 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.Furthermore, for the particular case of this subject, it must be borne in mind that It is the student's responsibility to avoid plagiarism in all its forms. In the event of detecting plagiarism, regardless of its scope, in any assessment activity (including internships), the current assessment regulations and disciplinary regime will be applied. In the specific case of internships, it must be borne in mind that these are considered a single activity so that fraud in one submission (A1 and/or A2 and/or A3) will be considered fraud in the entire activity (internships). In addition, the teacher will communicate the situation to the school's Management so that it can take the applicable measures in terms of the sanctioning regime. In the context of this subject, plagiarism also means using and/or adapting code that has not been developed entirely individually (or within the group in the case of group activities). Providing code that gives rise to plagiarism is also a form of plagiarism and will be treated in the same way. In summary, we can say that the evaluation activities must be solved in a strictly non-collaborative way (in the case of group activities, collaboration cannot transcend the group). The use of generative artificial intelligences (IAGs) must be limited to those aspects that are not fundamental in the context of the subject. They can be used, critically, as a mechanism to resolve doubts about the subject and/or to improve the writing of deliverable documents and/or as an aid in the generation of auxiliary code that is outside the scope of the subject topics. In the second case (improvement of the writing) the participation of IAG in the writing must be made explicit in the document. In the last case (code generation) it will be essential to mention its nature as “generated through IAG” by making explicit the model used and the prompt supplied, even if it has been subsequently personalized and/or modified. IAGs may not be used to generate programming code, not even in the form of fragments, when this code is within the scope of the subject topics and/or has an assessable nature. This prohibition remains even if the code is subsequently personalized and/or modified. In the event of doubts regarding the legitimacy or not of the use of IAGs, it is necessary to contact, a priori, the teaching staff of the subject. 

Recovery

- It is necessary to obtain a mark> = 5 in the final exam of recovery to pass the asignatura.

- The mark of the recovery exam will be applied to the A4 activity (and the formula Final Grade = A (1,2,3) · 0.5 + A4 · 0.5 will be applied again) 

- In case of passing the recovery (A (1,2,3) · 0.5 + A4 · 0.5> = 5) the maximum final mark of the subject will be 5 

Millington, Ian (2019). AI for games. Boca Raton, FL: CRC Press, Taylor & Francis Group.

Buckland, Matt (2009). Programming game AI by example. Plano, TX: Wordware Publ.