91411 - INTELLIGENT ROBOTIC SYSTEMS

Conoscenze e abilità da conseguire

At the end of the course, students have acquired knowledge and competencies for designing a system composed of one or more robots (here, we call "robot" an autonomous system which exists in the physical world, can sense its environment and can act on it to achieve some goals). In particular, students know the main models, methods, architectures and tools for programming robots equipped with nontrivial computational and cognitive capabilities.

Contenuti

Introduction to robotics
- Notions of robot and its behaviour in a physical environment
- Main issues in intelligent robotic systems design

Complex dynamical systems: basic definitions and concepts - propaedeutic to robotic topics
- Basic definitions: system, model, dynamics, etc.
- Discrete dynamical systems (notions of phase and state space, trajectory, attractor, bifurcation, phase transition, chaos)
- Examples: cellular automata, Boolean networks

Main methods and approaches for programming robotic systems
- Behavior-Based Robotics
- The Subsumption Architecture
- Artificial Evolution and Artificial Life
- Automatic design of robot programs
- Notable examples (e.g., notion of embodiment, sensory-motor coordination, niches)
- Fuzzy logic and fuzzy systems

- Behaviour trees

- Experimental evaluation and parameter tuning of control software for robots: practical guidelines

Robot learning
- Reinforcement learning
- Neural networks for robots

Robot planning
- Informed search algorithms. A* and its variants for path planning problems
- STRIPS and its extensions
- Nonlinear planning

- Navigation problems and main solution approaches

Lab activities
- Experiments with robotics simulators

Testi/Bibliografia

Course textbook: R. Pfeifer and C. Scheier, "Understanding intelligence", The MIT Press, 1999.


Additional books:

R. Pfeifer and J. Bongard, "How the body shapes the way we think", The MIT Press, 2007.

M. Mataric, "The Robotic Primer", The MIT Press, 2007.

U. Nehmzow, Robot Behaviour: Design, Description, Analysis
and Modelling, Springer, 2009.

Metodi didattici

The course is composed of class lessons and lab activities. The latter activities will be organised such that students will have the opportunity of tackling the main issues in devising control programs for robots and making experience of the knowledge acquired during the lessons in the class. In addition, projects in the lab will be planned so as to enable students to integrate also their studies made attending related courses.

Modalità di verifica e valutazione dell'apprendimento

The final exam aims at evaluating the extent to which students have reached the teaching objectives, i.e., the knowledge of the subjects taught in the course and the capability of designing and programming a robotic system. The exam consists in the presentation and the discussion of a project developed by the students (possibly in small groups) and the discussion of topics illustrated in the course. The main criteria are the evaluation of the knowledge acquired, the methodology used in the project and the scientific method used.

Strumenti a supporto della didattica

Students will be given teaching material prepared by the teacher (slides and papers published in journals and conferences). In addition, lab activities will make use of robotic simulators (e.g., ARGoS) and, whenever it is possible, of real robots.

Orario di ricevimento

Consulta il sito web di Andrea Roli