Symbolic State Space Optimization for Long Horizon Mobile Manipulation Planning

被引:0
|
作者
Zhang, Xiaohan [1 ]
Zhu, Yifeng [2 ]
Ding, Yan [1 ]
Jiang, Yuqian [2 ]
Zhu, Yuke [2 ]
Stone, Peter [2 ,3 ]
Zhang, Shiqi [1 ]
机构
[1] SUNY Binghamton, Dept Comp Sci, Binghamton, NY 13902 USA
[2] UT Austin, Dept Comp Sci, Austin, TX USA
[3] Sony AI, Austin, TX USA
关键词
TASK; ROBOT; PLATFORM;
D O I
10.1109/IROS55552.2023.10342224
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In existing task and motion planning (TAMP) research, it is a common assumption that experts manually specify the state space for task-level planning. A well-developed state space enables the desirable distribution of limited computational resources between task planning and motion planning. However, developing such task-level state spaces can be non-trivial in practice. In this paper, we consider a long horizon mobile manipulation domain including repeated navigation and manipulation. We propose Symbolic State Space Optimization (S3O) for computing a set of abstracted locations and their 2D geometric groundings for generating task-motion plans in such domains. Our approach has been extensively evaluated in simulation and demonstrated on a real mobile manipulator working on clearing up dining tables. Results show the superiority of the proposed method over TAMP baselines in task completion rate and execution time.
引用
收藏
页码:866 / 872
页数:7
相关论文
共 50 条
  • [1] Hierarchical Planning for Long-Horizon Manipulation with Geometric and Symbolic Scene Graphs
    Zhu, Yifeng
    Tremblay, Jonathan
    Birchfield, Stan
    Zhu, Yuke
    [J]. 2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 6541 - 6548
  • [2] An optimization approach to planning for mobile manipulation
    Berenson, Dmitry
    Kuffner, James
    Choset, Howie
    [J]. 2008 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-9, 2008, : 1187 - 1192
  • [3] SyDeBO: Symbolic-Decision-Embedded Bilevel Optimization for Long-Horizon Manipulation in Dynamic Environments
    Zhao, Zhigen
    Zhou, Ziyi
    Park, Michael
    Zhao, Ye
    [J]. IEEE ACCESS, 2021, 9 : 128817 - 128826
  • [4] Manipulation planning using learned symbolic state abstractions
    Dearden, Richard
    Burbridge, Chris
    [J]. ROBOTICS AND AUTONOMOUS SYSTEMS, 2014, 62 (03) : 355 - 365
  • [5] Symbolic manipulation of transfer functions and state space realizations
    Ho, DWC
    Lam, J
    Tin, SK
    Han, CY
    [J]. IEEE TRANSACTIONS ON EDUCATION, 1996, 39 (02) : 230 - 242
  • [6] Long horizon versus short horizon planning in dynamic optimization problems with incomplete information
    Herbert Dawid
    [J]. Economic Theory, 2005, 25 : 575 - 597
  • [7] Long horizon versus short horizon planning in dynamic optimization problems with incomplete information
    Dawid, H
    [J]. ECONOMIC THEORY, 2005, 25 (03) : 575 - 597
  • [8] State-space planning by integer optimization
    Kautz, Henry
    Walser, Joachim P.
    [J]. Proceedings of the National Conference on Artificial Intelligence, 1999, : 526 - 533
  • [9] State-space planning by integer optimization
    Kautz, H
    Walser, JP
    [J]. SIXTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-99)/ELEVENTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE (IAAI-99), 1999, : 526 - 533
  • [10] A symbolic symbolic state space representation
    Thierry-Mieg, Y
    Ilié, JM
    Poitrenaud, D
    [J]. FORMAL TECHNIQUES FOR NETWORKED AND DISTRIBUTED SYSTEMS - FORTE 2004, PROCEEDINGS, 2004, 3235 : 276 - 291