To be able to design behaviour-based control architectures to solve robotic tasks. To be able to analyse deliberative control architectures. To be able to apply basic Reinforcement Learning algorithms to learn basic robot behaviours. To be able to apply path planning algorithms
1. Overview of Control Architectures 2. Behaviour-based architectures 3. Path Planning 3.1. Bug algorithms 3.2. Configuration space 3.3. Potential functions 3.4. Topological maps 3.5. Graph search 3.6. Cell decompositions 3.7. Sampling-based algorithms 4. Robot learning 4.1. Reinforcement Learning 4.2. Q_learning 4.3. Path planning 4.4. Behaviour Learning
Tipus d’activitat Hores amb professor Hores sense professor Total Prova d'avaluació 4,00 12,00 16,00 Resolució d'exercicis 10,00 30,00 40,00 Sessió expositiva 20,00 15,00 35,00 Sessió pràctica 12,00 24,00 36,00 Total 46,00 81,00 127
Arkin (1998). Bahavior-based Robotics. MIT Press. Catàleg Choset, Howie M. (2005). Principles of robot motion : theory, algorithms, and implementation . Cambridge, Massachusetts : MIT Press. Catàleg Sutton, Richard S., Barto, Andrew G. (cop. 1998). Reinforcement learning : an introduction. Cambridge, Mass.: MIT Press.
Activitats d'avaluació: Descripció de l'activitat Avaluació de l'activitat % Laboratory Practical exercices in the laboratory. 40 Exercises Exercises will be proposed in class and students will send the answers through the web page. Solution will be given during next class. 30 Final Exam Theoretical and practical contents will be evaluated in the final exam. 40