AAAI-07 AI Video Competition: Accepted Videos

1. A service robot named Markovito (Videolectures MOV Mirror, 4:59, 107.0MB)
   Hector Hugo Aviles-Arriaga (1), Elva Corona-Xelhuantzi (1), Victor Manuel Jaquez Leal (2), Sergio Hernandez (2), Enrique Sucar (1), & Eduardo Morales (1)
   (1) Instituto Nacional de Astrofisica, Optica y Electronica, & (2) Tec de Monterrey Campus Cuernavaca
   
   This shows the Peoplebot Markovito as it delivers messages and objects between offices. It can perform speech communication, face recognition, global localization, uses a probabilistic grid map, and is controlled by a Factored MDP.

2. Dance evolution (Videolectures MOV, Mirror, 4:28, 388.8MB)
   Jeff Balogh, Greg Dubbin, & Michael Do
   Faculty Advisor: Kenneth O. Stanley
   University of Central Florida, USA
   Nominations: Best Student, Best Explanation
   
   The only submission from undergraduates, this unique video challenges AI to learn how to dance by demonstrating how neuroevolution can be used to (interactively) evolve dancing techniques.

3. k-nearest neighbor classification (Videolectures MPEG-4, Mirror, 3:21, 22.9MB)
   Antal van den Bosch
   Tilburg University, Netherlands
   Nominations: Best Video, Best Explanation
   In this short animated video the k-nearest neighbor classifier is introduced with simple 3D visuals. A real-world application, word pronunciation, is used to exemplify how the classifier learns and classifies. The video features a synthesized voice over.

4. Morphogenesis: Shaping swarms of intelligent robots (Videolectures XViD, Mirror, 4:57, 161.8MB)
   Anders Lyhne Christensen, Rehan O'Grady, & Marco Dorigo
   Université Libre de Bruxelles, Belgium
   Nominations: Best Video
   
   Describes, simulates, and demonstrates in hardware the utility of (rule-based) morphogenesis for shaping robot swarms.
   

5. Power agents at MDRS: The mobile agents project (Videolectures MOV (Mirror), 7:10, 99.6MB)
   Bill Clancey
   NASA Ames Research Center, USA
   Nominations: Best Demonstration, Most Visionary
   A comprehensive demonstration of the agents being used at the MDRS, scripted with inspiration from the HAL 9000. Permission granted for additional video length, although the main video ends at 5min.

6. Unmanned Aerial Vehicles: Selected Autonomous Functionalities (Videolectures MOV, Mirror, 1:08, 69.3MB)
   Patrick Doherty & Piotr Rudol
   Linkopings Universitet, Sweden
   Nominations: Best Short
   This short demo summarizes the capabilities of some autonomous unmanned air vehicles/helos, flying outdoors, that do not use GPS navigation techniques.

7. Autonomous UAV search and rescue (Videolectures MOV, Mirror, 5:40, 144.4MB)
   Patrick Doherty & Piotr Rudol
   Linkopings Universitet, Sweden
   Nominations: Best Video, Best Demonstration
   This longer demo films the application of some autonomous unmanned air vehicles/helos, flying outdoors, for a search and rescue operation. (A bit long.)

8. Leonardo: Goal assistance with divergent beliefs (Videolectures MOV, Mirror, 3:31, 110.9MB)
   Jesse Gray, Matt Berlin, & Cynthia Breazeal
   Massachusetts Institute of Technology, USA
   Nominations: Best Student, Best Demonstration
   This demonstrates the robot Leonardo's ability to reason and act competently in situations when the other (in this case, human) agents have different belief states.

9. Color-based object recognition (Videolectures AVI, Mirror, 2:53, 13.1MB)
   Jan-Mark Greusebroek & Frank Seinstra
   University of Amsterdam, Netherlands
   Nominations: Most Visionary
   This demonstrates a robodog that recognize objects in a "fetch" task. The software runs on a world-wide computing grid, distributing the computational load over several beowolf clusters.

10. Cosmo: The lifelike pedagogical agent (Videolectures MOV, Mirror, 4:37, 81.2MB)
    Arnav Jhala & Curtis Rawls
    North Carolina State University, USA
    Nominations: Best Explanation
    This features Cosmo, the Internet Advisor, created by NCSU's James Lester in the mid 90's. It presents Cosmo as an example of a lifelike pedagogical agent that used AI techniques to teach students interactively.

11. NERO 2.0: Neuro-evolving robotic operatives (Videolectures MOV, Mirror, 4:38 (black screen until 4:42, 83.9MB))
    Igor Karpov & Thomas Nelson
    University of Texas @ Austin, USA
    Nominations: Best Student
    This demonstrates the NERO real-time strategy game and the capabilities of its agents. The technology involves neuroevolution.

12. Two-on-two robot soccer (Videolectures WMV, Mirror, 0:59, 7.5MB)
    Keyong Li, Oliver Purwin, & Raffaello D'Andrea
    Cornell University, USA
    Nominations: Best Short
    A short demo of two-on-two robotic soccer, featuring the Cornell team's legacy and current players/robots.

13. Motion planning of multiple agents in virtual environments (Videolectures MPEG-4, Mirror, 3:07, 32.2MB)
    Yi Li & Kamal Gupta
    Simon Fraser University, Canada
    
    Describes and demonstrates in simulation the use of coordination graphs to avoid collisions of multiple agents in tasks requiring motion of multiple agents.

14. Artificial intelligence: An instance of Aibo ingenuity (Videolectures MOV, Mirror, 0:58, 3.8MB)
    Michael Littman
    Rutgers University, USA
    Nominations: Best Short
    This describes research related to using RL for, among other tasks, learning behaviors for an Aibo robot.

15. Robot swarm localization using trilateration (Videolectures WMV, Mirror, 4:58, 33.9MB)
    Paul Maxim & William Spears
    University of Wyoming, USA
    
    A description and demonstration of a robust approach for ground robot formation movement behaviors.

16. iAQ: A program that discovers rules (Videolectures MPEG, Mirror, 5:57, 379.3MB)
    Ryszard Michalski & Jarek Pietrzykowski
    George Mason University
    
    This video presents an entertaining program that discovers rules from data and outputs them in the form of English text and speech

17. Mira the robot head (Videolectures WMV, Mirror, 1:03, 14.0MB)
    John Murray, Chris Rowan, Alan Yau, Mark Elshaw, & Stefan Wermter
    University of Sunderland, England
    
    A short video demonstrating the speech communication, reasoning abilities, and humour of MIRA.

18. The Centibots 100 Robot Project (Videolectures MPEG-4, Mirror, 4:35, 65.3MB)
    Charlie Ortiz & Regis Vincent
    Stanford Research International, USA
    Nominations: Best Video, Best Demonstration
    The Centibots system was a multi-robotic system developed in part by SRI. Its team of 100 small robots were built from off-the-shelf components. This video describes the distributed robot control software and subsequent demonstration.

19. MARQS: Media album retrieval by query sketch (Videolectures AVI, Mirror, 0:59, 10.0MB)
    Brandon Paulson & Tracy Hammond
    Texas A&M University, USA
    Nominations: Best Short
    An advertisement-like short demo of a tool for retrieving photos from an album by sketching.

20. GMU BICA (Videolectures MOV, Mirror, 4:48, 176.9MB)
    Alexei V. Samsonovich, Kenneth A. De Jong, Giorgio A. Ascoli, & Mark A.Coletti
    George Mason University, USA
    
    This describes and demonstrates in simulation the capabilities of an agent controlled by a biologically-inspired cognitive architecture.

21. Humanoids for autonomous operations (Videolectures WMV, Mirror, 4:49, 48.2MB)
    Adrian Stoica
    NASA Jet Propulsion Laboratory, USA
    Nominations: Best Video
    The video describes a Humanoid robotics project at JPL.

22. Interactive derivation viewer (Videolectures MOV, Mirror, 4:59, 204.6MB)
    Steven Trac
    University of Miami, USA
    Nominations: Best Explanation
    This describes the IDV, a tool for graphically rendering derivations that are written in the Thousands of Problems for Theorem Provers (TPTP) language.

23. Autonomous robot cleaning crew (Videolectures WMV, Mirror, 2:57, 28.5MB)
    John Vannoy & Jing Xiao
    University of North Carolina @ Charlotte, USA
    Nominations: Best Demonstration
    De-centralized collaborative planning and simulation demo for coordinating agent/robot tasks.

24. How to say "No" to a robot (Videolectures AVI, Mirror, 1:27, 17.8MB)
    Hendrik Zender, Patric Jensfelt, & Oscar Martinez Mozos
    DFKI, Germany; KTH, Sweden; & University of Freiburg, Germany
    
    This describes an integrated robotic system for spatial understanding and situated interaction in indoor environments. Robot communication is performed using only natural language, but sometimes it needs more than a "natural" language to understand.