In this contribution we want to draw the readers attention to the advantages of controller architectures based on Dynamic Cell Structures (DCS) [5] for learning reactive behaviors of autonomous robots. These include incremental on-line learning, fast output calculation, a flexible integration of different learning rules and a close connection to fuzzy logic. The latter allows for incorporation of prior knowledge and to interpret learning with a DCS as fuzzy rule generation and ad aptation. After successful applications of DCS to tasks involving supervised learning, feedback error learning and incremental category learning, in this article we take reinforcement learning of reactive collision avoidance for an autonomous mobile robot as a further example to demonstrate the validity of our approach. More specifically, we employ a REINFORCE [23] algorithm in combination with an Adaptive Heuristic Critique (AHC) [21] to learn a continuous valued sensory motor mapping for obstacle avoidance with a TRC Labmate from delayed rein forcement. The sensory input consists of eight unprocessed sonar readings, the controller output is the continuous angular and forward velocity of the Labmate. The controller and the AHC are integrated within a single DCS network, and the resulting avoidance behavior of the robot can be analyzed as a set of fuzzy rules, each rule having an additional certainty value.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    An Integrated Architecture for Learning of Reactive Behaviors based on Dynamic Cell Structures


    Beteiligte:
    Bruske, Jörg (Autor:in) / Sommer, Gerald (Autor:in) / Ahrns, Ingo (Autor:in)

    Erscheinungsdatum :

    1996-01-01


    Medientyp :

    Paper


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    0 / 004 / 629



    Learning Collective Crowd Behaviors with Dynamic Pedestrian-Agents

    Zhou, B. / Tang, X. / Wang, X. | British Library Online Contents | 2015



    Dynamic Crushing Behaviors of Four Kinds of Auxetic Structures

    Qiang, Ge Cheng / Wang, Liangmo / Gao, Qiang | SAE Technical Papers | 2019


    Diagnosis of PEM fuel cell stack dynamic behaviors

    Chen, Jixin | Online Contents | 2008


    Learning collaborative impedance-based robot behaviors

    Rozo, Leonel / Calinon, Sylvain / Caldwell, Darwin et al. | BASE | 2013

    Freier Zugriff