Learning and Execution of Action Categories

Project Details

Description

ACAT focuses on the problem of how artificial systems (robots) can understand and utilize information made for humans. The ultimate purpose of ACAT is to equip a robot – on an ongoing basis – with abstract, functional knowledge about relations between actions and objects, leading to a system which can act meaningfully. The robot will be able to partially take over human tasks without time-consuming
programming procedures improving the efficiency of industrial processes. The main outcome of ACAT will be a robot-compiler which translates human understandable information into a robot-executable program.
AcronymACAT
StatusFinished
Effective start/end date01/03/201330/04/2016

Collaborative partners

  • University of Göttingen (Project partner) (lead)
  • University of Southern Denmark (Project partner)
  • Vytautas Magnus University (Project partner)
  • Jozef Stefan Institute, Dept. of Automatics, Biocyb. & Robotics, Ljubljana (Project partner)
  • Robotics Group, University of Bremen, Bremen, Germany.

Fingerprint

Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.