Towards multimodal neural robot learning

Stefan Wermter, Cornelius Weber, Mark Elshaw, Christo Panchev, Harry Erwin, Friedman Pulvermüller

    Research output: Contribution to journalArticlepeer-review

    34 Citations (Scopus)


    Learning by multimodal observation of vision and language offers a potentially powerful paradigm for robot learning. Recent experiments have shown that ‘mirror’ neurons are activated when an action is being performed, perceived, or verbally referred to. Different input modalities are processed by distributed cortical neuron ensembles for leg, arm and head actions. In this overview paper we consider this evidence from mirror neurons by integrating motor, vision and language representations in a learning robot.
    Original languageEnglish
    Pages (from-to)171-175
    Number of pages5
    JournalRobotics and Autonomous Systems
    Issue number2-3
    Publication statusPublished - 30 Jun 2004


    Dive into the research topics of 'Towards multimodal neural robot learning'. Together they form a unique fingerprint.

    Cite this