Abstract Reasoning with Symbol Discovery and Life-long Learning (TUBITAK-1001 Project)

Abstraction and abstract reasoning are among the most essential characteristics of high-level intelligence that distinguishes humans from other animals. High-level cognitive skills can only be achieved through abstract concepts, symbols representing these concepts, and rules that express relationships between symbols. This project aims to self-discover abstract concepts, symbols, and rules that allow complex reasoning by the robot. If the robots can achieve such abstract reasoning on their own, they can perform new tasks in completely novel environments by updating their cognitive skills, or by discovering new symbols and rules. If the objectives of this project are achieved, scientific foundations will be laid for robotic systems that learn life-long lasting symbols and rules through self-interacting with the environment and express various sensory-motor and cognitive tasks in a single framework.

News

  • We are organizing IROS 2022 Workshop on Life-long Learning of High-level Cognitive and Reasoning Skills (https://lifelongrobotics.github.io). [18/08/2022]
  • We are organizing RSS 2021 Workshop on Declarative and Neurosymbolic Representations in Robot Learning and Control (https://dnr-rob.github.io). [08/07/2021]
  • Hello World! [10/03/2021]

People

  • Alper Ahmetoglu
  • Emre Ugur
  • Gulsum Tuba Cibuk Girgin
  • Ibrahim Ozcan
  • Yigit Yildirim
  • A. Ahmetoglu, E. Oztop, E. Ugur, Learning Multi-Object Symbols for Manipulation with Attentive Deep Effect Predictors, (under review for Humanoids 2022) — arXiv:2208.01021
  • “Learning Multi-Object Symbols for Manipulation with Attentive Deep Effect Predictors” — Alper Ahmetoglu, Erhan Oztop, Emre Ugur — arXiv:2208.01021
  • A. Ahmetoglu, E. Ugur, M. Asada, E. Oztop, High-level Features for Resource Economy and Fast Learning in Skill Transfer, Advanced Robotics, pp. 1-13.
  • A. Ahmetoglu, M.Y. Seker, J. Piater, E. Oztop, E. Ugur, DeepSym: Deep Symbol Generation and Rule Learning from Unsupervised Continuous Robot Interaction for Planning, (accepted to JAIR). pdf, video