Projects

From Hande Celikkanat

(Difference between revisions)
m
m
Line 8: Line 8:
* Proposed how contextual information can emerge in this concept web, and developed an incremental variant of Latent Dirichlet Allocation for detecting contexts in an online and unsupervised manner.  
* Proposed how contextual information can emerge in this concept web, and developed an incremental variant of Latent Dirichlet Allocation for detecting contexts in an online and unsupervised manner.  
* On the iCub humanoid robot, showed how contextual information can be beneficial for improving object recognition, selecting appropriately safe actions, and computationally efficient planning.
* On the iCub humanoid robot, showed how contextual information can be beneficial for improving object recognition, selecting appropriately safe actions, and computationally efficient planning.
-
 
+
* A video is available [http://kovan.ceng.metu.edu.tr/~hande/ConceptWebContext_Video.mp4 here]
[http://www.rossiproject.net/rossi/ '''ROSSI: Emergence of Communication in Robots through Sensorimotor and Social Interaction'''] <br>
[http://www.rossiproject.net/rossi/ '''ROSSI: Emergence of Communication in Robots through Sensorimotor and Social Interaction'''] <br>

Revision as of 20:24, 4 May 2015

Development of Hierarchical Concepts in Humanoid Robots
Mar. 2014 - present
Funded by The Scientific and Technological Research Council of Turkey (TUBITAK) through project 111E287

  • Modeled human-like developmental learning of concepts, in a densely connected concept web based on a Markov Random Field, promoting their learning in relation to each other, thereby making them more robust and easily accessible.
  • Proposed a hybrid extension of the Markov Random Field to allow for directed information flow regarding spatial concepts.
  • Demonstrated the benefits of the probabilistic concept web in the humanoid robot iCub, over various scenarios of reasoning and object recognition.
  • Proposed how contextual information can emerge in this concept web, and developed an incremental variant of Latent Dirichlet Allocation for detecting contexts in an online and unsupervised manner.
  • On the iCub humanoid robot, showed how contextual information can be beneficial for improving object recognition, selecting appropriately safe actions, and computationally efficient planning.
  • A video is available here

ROSSI: Emergence of Communication in Robots through Sensorimotor and Social Interaction
Mar. 2010 - Jan. 2011
Funded by European Union through Framework Programme 7

  • Implemented a head-centered visual representation module (proposed by Grossberg et al.). The module relies on retinal images and current head-eye configuration information from the proprioceptive sensors of the robot in order to extract a pose-independent representation for environmental objects.
  • Implemented the Vector Integration to Endpoint (VITE) model for human-like movements on the iCub humanoid robot.

Controllable Robotic Swarm
Jun. 2006 - Sept. 2009
Funded by The Scientific and Technological Research Council of Turkey (TUBITAK) through project 104E066

  • Developed self-organized flocking behavior for Kobot robot (designed and implemented by KOVAN Research Lab. for swarm robotic studies)
  • Investigated the necessary and sufficient conditions for successful directional ``control of a self-organized flock by informed individuals spread throughout the flock, whose identities are not known to the other naive individuals
  • Took part in development of an OpenGL/ODE-based physical simulator for the Kobot robot platform
  • Developed a kernel module running on an onboard Linux processor for camera access on the Kobot robot platform
  • Developed an embedded omnidirectional vision algorithm for the Kobot robot platform
Navigation