ACAT Grant Agreement/Collaborative project (Learning and Execution of Action Categories)

  • Number of the Project: 600578 (FP7-ICT-2011-9)
  • Duration of the project: 1/03/2013 – 30/04/2016
  • Budget: 1.673.461,67 Litas
  • Main executor: Georg-August-Universitaet Goettingen Stiftung Oeffentlichen Rechts
  • Institution at VMU: Faculty of Informatics
  • Responsible person (s) at VMU: Daiva Vitkutė – Adžgauskienė

Aim of the project

Improving artificial systems (robots) to understand and utilize information made for humans

Actors involved

Vytauto Didžiojo universitetas, Syndansk University, University of Aalborg, Jozef Stefan Institute, University of Bremen.

Short description of the project

ACAT addresses the problem how artificial systems (robots) can understand and utilize information made for humans. For this, ACAT generates a dynamic process memory by extraction and storage of action categories from large bodies of human compatible sources (text, images). Our role in the project is to design appropriate strategies to automatically generate low level sensor motor processes that are needed by a robot to execute the generated action sequences.