Artificial Intelligence

Anders Jonsson

Presentation
The ability to integrate artificial intelligence capabilities and agency aboard of an autonomous robot is now a reality. The great
success of manipulation in robotics has now been expanded to platforms of robots that move in their environment and for which
the challenge of selecting their actions depends heavily on tracking their location by themselves.
This course explores the impact of intelligent capabilities aboard mobile robotics and examines the software architectures that
transform reactive behaviours into deliberative behaviours. We touch on the issues of middleware and illustrate this with the
software packages provided by ROS.
Associated skills
Basic skills
Understand the knowledge that provides a basis or opportunity to be original in the development and / or application of ideas, often in a research context where robots may be relevant.
Apply the knowledge acquired and their ability to solve problems in novel or poorly knownenvironments within broader (or multidisciplinary) contexts related to their area of study.
Integrate knowledge and face the complexity of making judgments based on information that, being incomplete or limited, includes reflections on social and ethical responsibilities linked to the application of their knowledge and judgment.
Learning skills that allow students to continue studying in a way that will need to be largely self-directed or autonomous.

Specific skills
E1) Apply the models and algorithms of machine learning, autonomous systems, interaction in natural language, mobile robotics and / or web intelligence to a problem of well-identified interactive intelligent systems. In particular, students will acquire in-depth experience with software programming tools and with the software architecture and middleware that enable the robotic behaviour.
E2) Program virtual agents so that they can interact with their environment, humans and / or other agents intelligently. In particular, students will develop expertise with reactive systems and the integration of deliberative capabilities.
E3) Identify new uses of models and algorithms in the field of interactive intelligent systems. In particular, students will also understand the main issues in algorithms for localisation, navigation and mapping.
E6) Present the result of a research project in the field of interactive intelligent systems in a scientific forum and in interaction with other researchers. In particular, develop a small package that demonstrates inquiry in mobile robotics.
Learning outcomes
E1) Solves problems related to interactive intelligent systems. In particular, students shall critically recognise and produce designs for software architectures and control architectures suited for robotic systems.
Identifies the appropriate models and algorithms to solve a specific problem in the field of interactive intelligent
systems. In particular, the student shall evaluate and contrast the techniques for robotic manipulation and robotic motion.
Evaluates the result of applying a model or algorithm to a specific problem. In particular, students shall appreciate the properties
of reactive systems and be able to compose complex behaviour from simpler behaviours of finite state machines.
E2) Uses software tools and environments autonomously for intelligent agent programming. Students shall become familiar with ROS as middleware and recognise the roles of middleware for robotics systems and the very relevant issues of properties contrasting the "push" approach versus the "pull" approach.
Implements stable algorithms that meet the quality requirements in relation to the required time and space. In particular, students shall apply kinematic models (as motion models) in the context of localisation to create the predictive step during the action phase of the localisation exercise.
E3) Recognizes the intentional domain of application of a model or algorithm in the field of interactive intelligent systems. In particular, use sensor models to incorporate the uncertainty of sensing in the revision of the belief that represent the notion of position and posture for the robot.
Describes limitations of a given model or algorithm for a new problem. In particular, recognise the common elements and the individual differences between the methods for map representation in localisation, as well for the algorithms that represent uncertainty and how they update such uncertainty for autonomous mobile robots.