Home ] Up ] Research ] Publications ] People ] History of Cog ] Job Opportunities ]

General Footage

 

  General Footage


The Cog Shop
MIT Artificial Intelligence Laboratory
545 Technology Square, #920
Cambridge, MA 02139

write to the Cog Documentation Project: cdp@ai.mit.edu

Latest Videos of Cog and Kismet!

The latest video footage of Cog and Kismet as of 2/19/99.

Cog:

  • Quicktime (large screen) -- (7.5 Meg)
  • Quicktime (smaller screen) -- (2.2 Meg)
  • Real Video (0.85 Meg)
  • Kismet:

  • Quicktime (large screen) -- (6 Meg)
  • Quicktime (smaller screen) -- (2 Meg)
  • Real Video (0.8 Meg)
  •  

    Overview of the Cog Project

    This video consists of interviews with several members of the Cog group demonstrating and discussing their most recent work. To view an accompanying article and alternate formats visit a page on cog at MIT Video Productions.

  • Quicktime (large screen) -- (28 Meg)
  • Quicktime (smaller screen) -- (15 Meg)
  • Quicktime (first 3 minutes of interviews lacks footage of Kismet) -- (10 Meg)
  •  

    Social Interaction

    This clip shows some 1995 footage of Cog interacting with Prof. Rod Brooks. The robot is attending to visual motion, and orienting its head and neck toward that motion. The arm and hand motion shown in this clip are simple repetitive motions which are not interactive.

  • Title: Social Interaction
  • Authors: Ferrell, Irie, Marjanovic, Scassellati, Williamson
  • Length: approximately 18 seconds
  • Quicktime (15 fps) -- (3.7 Meg)
  • Quicktime (30 fps) -- (7.5 Meg)
  • MPEG (15 fps) -- (2.6 Meg)
  • MPEG (30 fps) -- (5.1 Meg)

  • Reaching to a Visual Target

    One of the large sensori-motor integration tasks that has been implemented on Cog so far is the ability to reach to a visual target. Cog learns this task by trial and error. The first video clip shows the robot attempting to reach to where it is looking without any learning. Notice that the hand and eyes end up in very different positions.

  • Title: Learning to Reach to a Visual Target (no training)
  • Authors: Marjanovic, Scassellati, Williamson
  • Length: approximately 13 seconds
  • Quicktime (15 fps) -- (2.7 Meg)
  • Quicktime (30 fps) -- (5.4 Meg)
  • MPEG (15 fps) -- (1.5 Meg)
  • MPEG (30 fps) -- (3.1 Meg)

  • Each time the robot attempts to reach for a target and fails, it learns from that mistake. By waving its hand, the robot is able to determine the point that it actually reached toward, and can make an incremental refinement based on that error signal. This learning process is documented in the SAB-96 paper Self-Taught Visually-Guided Pointing for a Humanoid Robot by Marjanovic, Scassellati, and Williamson. The second video clip shows the images from the robot's camera during one training trial. The high speed change in camera position is the saccade that marks the beginning of the trial. After that, you can see the arm start to move. While the arm is in motion, we fade to the motion detection and grouping display, to show how the robot finds the arm within the visual field.

  • Title: Reaching to a visual target (CogCam)
  • Authors: Marjanovic, Scassellati, Williamson
  • Length: approximately 12 seconds
  • Quicktime (15 fps) -- (2.5 Meg)
  • Quicktime (30 fps) -- (5.0 Meg)
  • MPEG (15 fps) -- (1.1 Meg)
  • MPEG (30 fps) -- (2.2 Meg)
  •  


    The final clip shows the robot reaching to visual targets after approximately 3 hours of self training. After training, the robot was instructed to reach towards any moving object. This clip shows the robot reaching for a toy ball that is being waved in front of it. Notice that the hand reflexes are not yet integrated with the reaching behavior, so we need to place the ball into the robot's hand.

  • Title: Learning to Reach to a Visual Target (after 3 hours)
  • Authors: Marjanovic, Scassellati, Williamson
  • Length: approximately 18 seconds
  • Quicktime (15 fps) -- (3.9 Meg)
  • Quicktime (30 fps) -- (7.7 Meg)
  • MPEG (15 fps) -- (2.2 Meg)
  • MPEG (30 fps) -- (4.4 Meg)

  •  


    Representatives of the press who are interested in acquiring further information about the Cog project should contact Elizabeth Thomson, thomson@mit.edu, from the MIT News Office,  http://web.mit.edu/newsoffice/www/ .

     

    Home ] Up ] Research ] Publications ] People ] History of Cog ] Job Opportunities ]