Autonomous learning of target decision strategies without communications for continuous coordinated cleaning tasks

Keisuke Yoneda, Chihiro Kato, Toshiharu Sugawara

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    9 Citations (Scopus)

    Abstract

    We propose a method for the autonomous learning of target decision strategies for coordination in the continuous cleaning domain. With ongoing advances in computer and sensor technologies, we can expect robot applications for covering large areas that often require coordinated/cooperative activities by multiple robots. In this paper, we focus the cleaning tasks by multiple robots or by agents, software to control the robots. We assume that agents cannot directly exchange internal information such as plans and targets for coordination, but rather individually learn their target decision strategies by observing how much trash/dirt has been vacuumed up in the multi-agent system environments. We experimentally evaluated the proposed method by comparing its performance with those obtained by the regimes of agents with a single strategy. Results showed that the proposed method enables agents to select target decision strategies from their own perspectives, resulting in the appropriate combinations of multiple strategies.

    Original languageEnglish
    Title of host publicationProceedings - 2013 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013
    PublisherIEEE Computer Society
    Pages216-223
    Number of pages8
    Volume2
    ISBN (Print)9781479929023
    DOIs
    Publication statusPublished - 2013
    Event2013 12th IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013 - Atlanta, GA
    Duration: 2013 Nov 172013 Nov 20

    Other

    Other2013 12th IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013
    CityAtlanta, GA
    Period13/11/1713/11/20

    Fingerprint

    Cleaning
    Robots
    Communication
    Robot applications
    Software agents
    Multi agent systems
    Sensors

    Keywords

    • Coordination
    • Learning
    • Multi-robot sweeping
    • Robot patrolling

    ASJC Scopus subject areas

    • Artificial Intelligence

    Cite this

    Yoneda, K., Kato, C., & Sugawara, T. (2013). Autonomous learning of target decision strategies without communications for continuous coordinated cleaning tasks. In Proceedings - 2013 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013 (Vol. 2, pp. 216-223). [6690792] IEEE Computer Society. https://doi.org/10.1109/WI-IAT.2013.112

    Autonomous learning of target decision strategies without communications for continuous coordinated cleaning tasks. / Yoneda, Keisuke; Kato, Chihiro; Sugawara, Toshiharu.

    Proceedings - 2013 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013. Vol. 2 IEEE Computer Society, 2013. p. 216-223 6690792.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Yoneda, K, Kato, C & Sugawara, T 2013, Autonomous learning of target decision strategies without communications for continuous coordinated cleaning tasks. in Proceedings - 2013 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013. vol. 2, 6690792, IEEE Computer Society, pp. 216-223, 2013 12th IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013, Atlanta, GA, 13/11/17. https://doi.org/10.1109/WI-IAT.2013.112
    Yoneda K, Kato C, Sugawara T. Autonomous learning of target decision strategies without communications for continuous coordinated cleaning tasks. In Proceedings - 2013 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013. Vol. 2. IEEE Computer Society. 2013. p. 216-223. 6690792 https://doi.org/10.1109/WI-IAT.2013.112
    Yoneda, Keisuke ; Kato, Chihiro ; Sugawara, Toshiharu. / Autonomous learning of target decision strategies without communications for continuous coordinated cleaning tasks. Proceedings - 2013 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013. Vol. 2 IEEE Computer Society, 2013. pp. 216-223
    @inproceedings{138d5229cdf348c98e02c7b45d0facbe,
    title = "Autonomous learning of target decision strategies without communications for continuous coordinated cleaning tasks",
    abstract = "We propose a method for the autonomous learning of target decision strategies for coordination in the continuous cleaning domain. With ongoing advances in computer and sensor technologies, we can expect robot applications for covering large areas that often require coordinated/cooperative activities by multiple robots. In this paper, we focus the cleaning tasks by multiple robots or by agents, software to control the robots. We assume that agents cannot directly exchange internal information such as plans and targets for coordination, but rather individually learn their target decision strategies by observing how much trash/dirt has been vacuumed up in the multi-agent system environments. We experimentally evaluated the proposed method by comparing its performance with those obtained by the regimes of agents with a single strategy. Results showed that the proposed method enables agents to select target decision strategies from their own perspectives, resulting in the appropriate combinations of multiple strategies.",
    keywords = "Coordination, Learning, Multi-robot sweeping, Robot patrolling",
    author = "Keisuke Yoneda and Chihiro Kato and Toshiharu Sugawara",
    year = "2013",
    doi = "10.1109/WI-IAT.2013.112",
    language = "English",
    isbn = "9781479929023",
    volume = "2",
    pages = "216--223",
    booktitle = "Proceedings - 2013 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - Autonomous learning of target decision strategies without communications for continuous coordinated cleaning tasks

    AU - Yoneda, Keisuke

    AU - Kato, Chihiro

    AU - Sugawara, Toshiharu

    PY - 2013

    Y1 - 2013

    N2 - We propose a method for the autonomous learning of target decision strategies for coordination in the continuous cleaning domain. With ongoing advances in computer and sensor technologies, we can expect robot applications for covering large areas that often require coordinated/cooperative activities by multiple robots. In this paper, we focus the cleaning tasks by multiple robots or by agents, software to control the robots. We assume that agents cannot directly exchange internal information such as plans and targets for coordination, but rather individually learn their target decision strategies by observing how much trash/dirt has been vacuumed up in the multi-agent system environments. We experimentally evaluated the proposed method by comparing its performance with those obtained by the regimes of agents with a single strategy. Results showed that the proposed method enables agents to select target decision strategies from their own perspectives, resulting in the appropriate combinations of multiple strategies.

    AB - We propose a method for the autonomous learning of target decision strategies for coordination in the continuous cleaning domain. With ongoing advances in computer and sensor technologies, we can expect robot applications for covering large areas that often require coordinated/cooperative activities by multiple robots. In this paper, we focus the cleaning tasks by multiple robots or by agents, software to control the robots. We assume that agents cannot directly exchange internal information such as plans and targets for coordination, but rather individually learn their target decision strategies by observing how much trash/dirt has been vacuumed up in the multi-agent system environments. We experimentally evaluated the proposed method by comparing its performance with those obtained by the regimes of agents with a single strategy. Results showed that the proposed method enables agents to select target decision strategies from their own perspectives, resulting in the appropriate combinations of multiple strategies.

    KW - Coordination

    KW - Learning

    KW - Multi-robot sweeping

    KW - Robot patrolling

    UR - http://www.scopus.com/inward/record.url?scp=84893330539&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84893330539&partnerID=8YFLogxK

    U2 - 10.1109/WI-IAT.2013.112

    DO - 10.1109/WI-IAT.2013.112

    M3 - Conference contribution

    SN - 9781479929023

    VL - 2

    SP - 216

    EP - 223

    BT - Proceedings - 2013 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2013

    PB - IEEE Computer Society

    ER -