Cognitive Systems that Self-Understand and Self-Extend

01.05.2008 - 30.06.2012
Forschungsförderungsprojekt
CogX sets out to understand the principles according to which cognitive systems should be built if they are to handle situations unforeseen by their designers, other forms of novelty, and open-ended, challenging environments with uncertainty and change. Our aim is to meet this by creating a theory ¿ grounded and evaluated in robots ¿ of how a cognitive system can model its own knowledge, use this to cope with uncertainty and novelty during task execution, extend its own abilities and knowledge, and extend its own understanding of those abilities. A specific, if very simple example of the kind of task that we will tackle is a domestic robot assistant or gopher that is asked by a human to: ¿Please bring me the box of cornflakes.¿ There are many kinds of knowledge gaps that could be present (we will not tackle all of these): ¿ What this particular box looks like. ¿ Which room this particular item is currently in. ¿ What cereal boxes look like in general. ¿ Where cereal boxes are typically to be found within a house. ¿ How to grasp this particular packet. ¿ How to grasp cereal packets in general. ¿ What the cornflakes box is to be used for by the human. The robot will have to fill the knowledge gaps necessary to complete the task, but this also offers opportunities for learning. To self-extend, the robot must identify and exploit these opportunities. We will allow this learning to be curiosity driven. This provides us, within the confines of our scenario, with the ability to study mechanisms able to generate a spectrum of behaviours from purely task driven information gathering to purely curiosity driven learning. To be flexible the robot must be able to do both. It must also know how to trade-off efficient execution of the current task ¿ find out where the box is and get it ¿ against curiosity driven learning of what might be useful in future ¿ find out where you can usually find cereal boxes, or spend time when you find it performing grasps and pushes on it to see how it behaves. One extreme of the spectrum we can characterise as a task focused robot assistant, the other as a kind of curious robotic child scientist that tarries while performing its assigned task in order to make discoveries and experiments. One of our objectives is to show how to embed both these characteristics in the same system, and how architectural mechanisms can allow an operator ¿ or perhaps a higher order system in the robot ¿ to alter their relative priority, and thus the behaviour of the robot.

Personen

Projektleiter_in

Projektmitarbeiter_innen

Institut

Förderungmittel

  • European Commission (EU) 6.RP: IST - Technologien der Informationsgesellschaft 6.Rahmenprogramm für Forschung Europäische Kommission - Rahmenprogamme Europäische Kommission Ausschreibungskennung Fp7 1st Call Antragsnummer 215181

Forschungsschwerpunkte

  • Cognitive and adaptive Automation and Robotics: 100%

Schlagwörter

DeutschEnglisch
Kognitive SystemeCognitive Systems
Roboter lernt greifenLearning to grasp
Objektefunktionen verstehenReasoning about objects function
Vorhersage von GreifoperationenPredicting hand-object interaction
BildverarbeitungImage Processing

Externe Partner_innen

  • Deutsches Forschungszentrum für Künstliche Intelligenz GmbH
  • THE UNIVERSITY OF BIRMINGHAM
  • Kungliga Tekniska Hoegskolan
  • University of Lubljana
  • Albert-Ludwigs-Universität Freiburg

Publikationen