Na materia de Robótica estúdanse os principais conceptos de robótica autónoma, facendo énfase no deseño automático de estratexias de control. Para iso, o contido da materia parte das estratexias clásicas de control para chegar ás máis actuais baseadas en conceptos da intelixencia computacional, tales como as redes neuronais, os algoritmos evolutivos e a aprendizaxe por reforzo.
Study programme competencies
Code
Study programme competences / results
A35
Capacidade de analizar, avaliar e seleccionar as plataformas hárdware e sóftware máis acaídas para o soporte de aplicacións embarcadas e de tempo real.
A43
Capacidade para adquirir, obter, formalizar e representar o coñecemento humano nunha forma computable para a resolución de problemas mediante un sistema informático en calquera ámbito de aplicación, particularmente os relacionados con aspectos de computación, percepción e actuación en ambientes ou contornos intelixentes.
B1
Capacidade de resolución de problemas
B3
Capacidade de análise e síntese
B9
Capacidade para xerar novas ideas (creatividade)
C6
Valorar criticamente o coñecemento, a tecnoloxía e a información dispoñible para resolver os problemas cos que deben enfrontarse.
C8
Valorar a importancia que ten a investigación, a innovación e o desenvolvemento tecnolóxico no avance socioeconómico e cultural da sociedade.
Learning aims
Learning outcomes
Study programme competences / results
Develop an autonomous control system for its operation in a real environment
A43
B1 B3 B9
Know the non-resolved problems in autonomous robotics
C6 C8
Know the problems of sensing and actuation in systems that operate in the real world and real time
A35
C6 C8
Know the problems of knowledge representation in autonomous robotics
C6 C8
Know the problems to tackle when an autonomous robotic control system is developed
A43
B9
C6 C8
Contents
Topic
Sub-topic
Introduction to autonomous robotics
¿What is an autonomous robot?
History
Sensors and actuators
Behaviors
Planning
Learning and evolution
Elements of a robotic system
Robotic system
Actuators and effectors
Sensors
Control architectures
Behavior-based robotics
Antecedents
Classical control architectures
Control architectures
Knowledge-based robotics
Knowledge
Traditional deliberative robotics
Navigation
Hybrid approximations
Main hybrid architectures
Cognitive robotics
Evolutionary robotics
Evolutionary algorithms
Application to robotics
Learning in autonomous robotics
Learning in classifier systems
Reinforcement learning: Q-learning
Combination of reinforcement and connectionist learning
Planning
Methodologies / tests
Competencies / Results
Teaching hours (in-person & virtual)
Student’s personal work hours
Total hours
Laboratory practice
A43 B1 B3 B9
21
21
42
Supervised projects
A35 B3 B9
0
30
30
Oral presentation
B3 C8
4
28
32
Guest lecture / keynote speech
A35 C8 C6
21
21
42
Personalized attention
4
0
4
(*)The information in the planning table is for guidance only and does not take into account the heterogeneity of the students.
Methodologies
Methodologies
Description
Laboratory practice
Lab. sessions in which the teachers will explain the robotic platform and its development software in detail. Moreover, during these sessions, the students must perform the design, implementation and validation of the supervised projects under the supervision of a teacher.
Supervised projects
Programming exercises that must be developed using the selected robotic platform. These exercises will be carried out in an autonomous way and their progress will be supervised by the teachers
Oral presentation
Theoretical work about a specific topic from the contents that will be orally presented and discussed with other students
Guest lecture / keynote speech
Oral exposition by the teachers of the theory of the subject.
Personalized attention
Methodologies
Laboratory practice
Supervised projects
Oral presentation
Description
During the lab practices and tutorials, the student can consult the teacher all the doubts that appear about the realization of the formulated practical problems or about the use of the simulator or the real robot.
Supervised projects: It is recommendable the use of a personal assistance in these activities to resolve conceptual doubts or procedures than can appear during the resolution of the practical problems. Also, the personal assistance will be focused on in the explanation, by the student, of the proposed solution.
Oral presentation: the students' progress in their theoretical work must be supervised by the teachers, both in terms of contents and format.
Assessment
Methodologies
Competencies / Results
Description
Qualification
Laboratory practice
A43 B1 B3 B9
The attendance to the laboratory classes will be considered in the final mark
5
Guest lecture / keynote speech
A35 C8 C6
The attendance to the keynote speeches will be considered in the final mark
5
Supervised projects
A35 B3 B9
Different programming projects will be proposed along the course that must be carried out in an autonomous way by the student and that will be presented and explained to the teachers afterwards. It is mandatory to pass this methodology independently in order to pass the whole subject.
50
Oral presentation
B3 C8
The oral presentation, the participation in the discussion and the written inform will be considered in the final mark. It is mandatory to pass this methodology independently in order to pass the whole subject.
40
Assessment comments
Evaluation of this course is based on independently overcoming the two main methodologies: supervised projects and oral presentation. The first one focuses on the practical demonstration of the knowledge and skills acquired to solve problems in autonomous robotics, and the second one in the completion and presentation of a paper on a specific topic within theoretical agenda. Thus, if the student does not pass the subject in the ordinary call, he / she shall repeat all activities that were not passed in the extraordinary call. As an example, if a student passed the oral presentation but failed the supervised projects, he / she shall repeat these. Students with part-time enrollment can displace the 5% of the qualification of the attendance to the other activities, both in theory and in practice, in case they can not regularly attend classes. This change in the qualification methodology shall be applied to teachers of the subject at the beginning of the course.
Sources of information
Basic
Bekey, A. (2005). Autonomous Robots. MIT Press
Arkin, R.C. (1998). Behavior Based Robotics. MIT Press
Santos, J., Duro, R.J. (2005). Evolución Artificial y Robótica Autónoma. RA-MA
Mataric, Maja J. (2007). The Robotics Primer. MIT Press
Complementary
Santos, J. (2007). Vida Artificial. Realizaciones Computacionales. ServicioPublicaciones UDC
Floreano, D. and Mattiussi, C. (2008). Bio-Inspired Artificial Intelligence. Tema 7. MIT Press
Salido, J. (2009). Cibernética aplicada. Robots educativos. Ra-Ma
Nolfi, S., Floreano, D. (2000). Evolutionary Robotics. MIT Press
Thurn, S., Burgard, W., Fox, D. (2005). Probabilistic Robotics. MIT Press
Sutton, R.S., Burton A.G. (1998). Reinforcement Learning. MIT Press
Pfeifer, R. and Scheier, C. (1999). Understanding Intelligence. MIT Press
Recommendations
Subjects that it is recommended to have taken before
Intelligent Systems/614G01020
Knowledge Representation and Automatic Reasoning/614G01036
Intelligent Systems Development/614G01037
Machine Learning/614G01038
Subjects that are recommended to be taken simultaneously
Subjects that continue the syllabus
Other comments
Para axudar a conseguir unha contorna inmediata sustentable e cumprir co obxectivo da acción número 5: "Docencia e investigación saudable e sustentable ambiental e social" do "Plan de Acción Green Campus Ferrol" a entrega dos traballos documentais que se realicen nesta materia:
1. Solicitarase en formato virtual e/ou soporte informático
2. Realizarase a través de Moodle, en formato dixital sen necesidade de imprimilos
3. De se realizar en papel:
- Non se empregarán plásticos.
- Realizaranse impresións a dobre cara.
- Empregarase papel reciclado.
- Evitarase a impresión de borradores.
(*)The teaching guide is the document in which the URV publishes the information about all its courses. It is a public document and cannot be modified. Only in exceptional cases can it be revised by the competent agent or duly revised so that it is in line with current legislation.