Learning to coordinate behaviors in soft behavior-based systems using reinforcement learning

被引:0
|
作者
Azar, Mohammad G. [1 ]
Ahmadabadi, Majid Nili [1 ]
Farahmand, Amir Massoud [1 ,2 ]
Araabi, Babak Nadjar [1 ]
机构
[1] Univ Tehran, Dept Elect & Comp Engn, Tehran 14174, Iran
[2] Univ Alberta, Dept Comp Sci, Edmonton, AB T6G 2M7, Canada
来源
2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10 | 2006年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Behavior-based systems have been successfully used in control and robotics applications. In traditional behavior-based systems, only a single behavior controls the agent in any time step. However, this behavior arbitration is not appropriate for many complex tasks. In this paper, we propose Hierarchical Soft Behavior-based Architecture that uses the concept of soft suppression to coordinate flexibly between behaviors. In our method, we use reinforcement learning to find an appropriate amount of suppression for each behavior in the architecture, in addition to learn the internal mechanism of each behavior. Several experiments are provided to show the effectiveness of our method in the mobile robot navigation task.
引用
收藏
页码:241 / +
页数:2
相关论文
共 50 条
  • [21] An Android Behavior-Based Malware Detection Method using Machine Learning
    Chang, Wei-Ling
    Sun, Hung-Min
    Wu, Wei
    2016 IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, COMMUNICATIONS AND COMPUTING (ICSPCC), 2016,
  • [22] Task-oriented multi-robot learning in behavior-based systems
    Parker, LE
    IROS 96 - PROCEEDINGS OF THE 1996 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS - ROBOTIC INTELLIGENCE INTERACTING WITH DYNAMIC WORLDS, VOLS 1-3, 1996, : 1478 - 1487
  • [23] A Behavior-Based Reinforcement Learning Approach to Control Walking Bipedal Robots Under Unknown Disturbances
    Beranek, Richard
    Karimi, Masoud
    Ahmadi, Mojtaba
    IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2022, 27 (05) : 2710 - 2720
  • [24] Behavior learning of hierarchical behavior-based controller for brachiation robot
    Fukuda, T
    Hasegawa, Y
    SYSTEMATIC ORGANISATION OF INFORMATION IN FUZZY SYSTEMS, 2003, 184 : 359 - 371
  • [25] Fuzzy behavior-based control trained by module learning to acquire the adaptive behaviors of mobile robots
    Izumi, K
    Watanabe, K
    MATHEMATICS AND COMPUTERS IN SIMULATION, 2000, 51 (3-4) : 233 - 243
  • [26] Learning to ground fact symbols in behavior-based robots
    Hertzberg, J
    Jaeger, H
    Schönherr, F
    ECAI 2002: 15TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2002, 77 : 708 - 712
  • [27] Behavior-based learning fuzzy rules for mobile robots
    Thongchai, S
    PROCEEDINGS OF THE 2002 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2002, 1-6 : 995 - 1000
  • [28] Learning to coordinate controllers - Reinforcement learning on a control basis
    Huber, M
    Grupen, RA
    IJCAI-97 - PROCEEDINGS OF THE FIFTEENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOLS 1 AND 2, 1997, : 1366 - 1371
  • [29] TriDeepRec: a hybrid deep learning approach to content- and behavior-based recommendation systems
    Ghadami, Amirhossein
    Tran, Thomas
    USER MODELING AND USER-ADAPTED INTERACTION, 2024, 34 (05) : 2085 - 2114
  • [30] Behavior-Based Collision Avoidance Using a Cylinder-Coordinate Octree
    Schmidt, Daniel
    Goeckel, Fabian
    Berns, Karsten
    INTELLIGENT AUTONOMOUS SYSTEMS 14, 2017, 531 : 143 - 155