Artificial Intelligence – Methods and Applications

Part 1, theory, 4.5 credits. The course provides theoretical and methodological knowledge and skills in classical AI (artificial intelligence) and robotics. Topics covered: Heuristics for search. Search for games. Applied predicate logic. Classical planning: heuristics. Knowledge representation. Probability theory: axioms, conditional probability, Bayes’ rule. Bayesian networks. Probabilistic reasoning over time, Hidden Markov Models. Decision trees and learning. Robotics: reinforcement learning, learning from demonstration, hybrid architectures, motion planning, odometry, metric and topological route planning, localization and map generation.

Part 2, laboratory, 3 credits. In the laboratory part some of the theories and techniques discussed in the theoretical part are put into practice. This part consists of a series of mandatory laboratory assignments, in part carried out with physical robots or advanced simulators.