Human-like Artificial Agents (Summer 2016/2017)

Course Info

In this course, we will study human-like artificial agents, that is autonomous intelligent agents situated in a virtual environment similar to real world that act like humans. The course gives an overview of types of such agents and their architectures with the emphasis on the problem of action selection. The course also focuses on solving practical issues related to real-time and partially observable environments. The course is taught at MFF UK as NAIL068.

Schedule (SIS)

Lectures: Thursdays, 17:20, S4 (we start 23.2.2017)

Labs: Tuesdays, 15:40, SW2 (we start 28.2.2017)

Plan & Slides

No. Date Topic Lecturer Slides
1. 23.2.2017 Introduction Cyril Brom, Jakub Gemrot Lecture, Gardener Agent Rules, Labs Promo
2. 2.3.2017 Reactive Planning – Part I Jakub Gemrot Lecture
3. 9.3.2017 Reactive Planning – Part II Jakub Gemrot Lecture
4. 16.3.2017 Reactive Planning – Part III Jakub Gemrot Lecture
5. 23.3.2017 Minimally cognitive robotics: body representations
and sensorimotor contingencies in quadrupedal
and humanoid robots
Matěj Hoffmann
(Faculty of Electrical Engineering,
Czech Technical University in Prague;
Cub Facility, Istituto Italiano di Tecnologia)
Lecture
6. 30.3.2017 Reactive Planning – Part IV Jakub Gemrot Lecture
7. 6.4.2017 Steerings, Environment Awareness
Path-finding & Navigation techniques
Jakub Gemrot Spatial Aweraness
Path-finding (in CZE)
Steerings
13.4.2017 Easter holidays!
8. 20.4.2017 AI in Kingdome Come: Deliverance Tomáš Plch (Warhorse Studios) TBD
9. 27.4.2017 17:20 AI in Kingdome Come: Deliverance
18:00 Neural networks for action selection
Martin Černý (Warhorse Studios)
Cyril Brom
NN Slides, BDI Slides
10. 4.5.2017 Ethologically inspired architectures for action selection I
User study: debriefing
Cyril Brom
Lukáš Kolek
Ethology Slides I
CS3889 Debriefing
11. 11.5.2017 Ethologically inspired architectures for action selection II Cyril Brom Ethology Slides II (in Czech)
12. 18.5.2017 Level-of-detail AI, Episodic memory Cyril Brom TBD

Exam for FF UK students

Exams for New Media Studies students: Action-selection for virtual characters: finite state machines, if-then rules, behavior trees. Navigation: A* (basic principles), steering rules, terrain representation.

Experiment (for both MFF & FF UK students)

Attending the experiment is mandatory! You will receive no credits if you miss this.

Computer games and attitudes change

Popularity of the computer games is on its rise. Historical computer games became one of the most common and successful forms through which the past is engaged. However the research about the effects of those games on their players is still limited. This user study is focused on player´s attitudes towards the historical topics represented in the game.

Place: Malostranské náměstí 2/25, Prague 1 in a room SW1
Time:  9:30 – 12:00
Possible Dates:
1) 7.4. 2017
2) 14.4. 2017
3) 21.4. 2017
4) 28.4. 2017

It is necessary that you choose ONE date which suits you the best through the link provided you via email. Deadline for the registration is 16.3.2017

Do it as soon as possible since there is limitation of 6 participants per date!

At the end of the semester will be organised debriefing session regarding the design of the experiment.

In case of any trouble, please contact the administrator of the user-study: lukaskolek(at)live.com

Slides Archive (2010-2015)

  1. Introduction (in Czech)
  2. Reactive planning, If-then rules, Finite state machines, POSH (updated 130227)
  3. Pathfinding (in Czech)
  4. Steering (updated spring 2012)
  5. Creatures, neural networks, evolutionary algorithms
  6. Tyrrell (free-flow hierarchy)
  7. Computational ethology (in Czech)
  8. Fuzzy approach, emotions (Champandard)
  9. Belief Desire Intention
  10. Representation – logic, RETE, affordances, deictic representation
  11. Agents vs. Animats, Wooldridge, FIPA, speech acts
  12. Soar intro
  13. Storytelling intro
  14. Spatial memory & psychological experiments (updated 130425)
  15. Slides on emotions (2007, in Czech)