Sistemi intelligenti robotici 2013/2014

Course contents

• Complex dynamical systems: basic definitions and concepts - propaedeutic to robotic topics
• Main methods and approaches for programming robotic systems
  • Behavior-Based Robotics 
  • The Subsumption Architecture 
  • Artificial Evolution and Artificial Life 
  • The Dynamical Systems Approach 
  • Automatic design of robot programs
  • Relations with machine learning and planning
• Notable examples (e.g., notion of embodiment, sensory-motor coordination, niches) 

AI*IA - Italian association for artificial intelligence

The Italian association for artificial intelligence is a non profit association promoting AI research. Website: www.aixia.it For further information, students can also contact Andrea Roli.

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.

• 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
  • Complex networks in brief (random graphs, scale-free and small-world networks and applications)
• Main methods and approaches for programming robotic systems
  • Behavior-Based Robotics
  • The Subsumption Architecture
  • Artificial Evolution and Artificial Life
  • The Dynamical Systems Approach
  • Automatic design of robot programs
  • Notable examples (e.g., notion of embodiment, sensory-motor coordination, niches)
  • Relations with machine learning and planning
• Lab activities: experiments in simulations and with real robots
  • Robot simulators
  • Programming of real robots (e.g., e-puck, Lego Mindstorm)

• 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.

The course is composed of class lessons and lab activities. The latter activities will be organised such that students will have the opportunity of 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.

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). The main criteria are the evaluation of the knowledge acquired, the methodology used in the project and the scientific method used.

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., Webots and ARGoS) and real robots, such as e-puck and Lego Mindstorm robots.