The Value of Planning for Infinite-Horizon Model Predictive Control

被引:5
|
作者
Hatch, Nathan
Boots, Byron
机构
来源
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) | 2021年
关键词
D O I
10.1109/ICRA48506.2021.9561718
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Model Predictive Control (MPC) is a classic tool for optimal control of complex, real-world systems. Although it has been successfully applied to a wide range of challenging tasks in robotics, it is fundamentally limited by the prediction horizon, which, if too short, will result in myopic decisions. Recently, several papers have suggested using a learned value function as the terminal cost for MPC. If the value function is accurate, it effectively allows MPC to reason over an infinite horizon. Unfortunately, Reinforcement Learning (RL) solutions to value function approximation can be difficult to realize for robotics tasks. In this paper, we suggest a more efficient method for value function approximation that applies to goal-directed problems, like reaching and navigation. In these problems, MPC is often formulated to track a path or trajectory returned by a planner. However, this strategy is brittle in that unexpected perturbations to the robot will require replanning, which can be costly at runtime. Instead, we show how the intermediate data structures used by modern planners can be interpreted as an approximate value function. We show that that this value function can be used by MPC directly, resulting in more efficient and resilient behavior at runtime.
引用
收藏
页码:7372 / 7378
页数:7
相关论文
共 50 条
  • [11] On infinite-horizon optimal control problems
    Effati, S
    Kamyad, V
    Kamyabi-Gol, RA
    ZEITSCHRIFT FUR ANALYSIS UND IHRE ANWENDUNGEN, 2000, 19 (01): : 269 - 278
  • [12] Value Functions and Transversality Conditions for Infinite-Horizon Optimal Control Problems
    Nobusumi Sagara
    Set-Valued and Variational Analysis, 2010, 18 : 1 - 28
  • [13] Rebuttal to Comments on "Constrained Infinite-Horizon Model Predictive Control for Fuzzy-Discrete-Time Systems"
    Xia, Yuanqing
    Yang, Hongjiu
    Shi, Peng
    Fu, Mengyin
    IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2011, 19 (03) : 601 - 602
  • [14] Infinite-horizon optimal control problems in economics
    Aseev, S. M.
    Besov, K. O.
    Kryazhimskiy, A. V.
    RUSSIAN MATHEMATICAL SURVEYS, 2012, 67 (02) : 195 - 253
  • [15] Infinite-horizon stable control of a parabolic equation
    Blizorukova, M. S.
    COMPUTATIONAL MATHEMATICS AND MATHEMATICAL PHYSICS, 2015, 55 (09) : 1461 - 1467
  • [16] Infinite-horizon boundary control of distributed systems
    Maksimov, V. I.
    Osipov, Yu. S.
    COMPUTATIONAL MATHEMATICS AND MATHEMATICAL PHYSICS, 2016, 56 (01) : 14 - 25
  • [17] Erratum to: Value Functions and Transversality Conditions for Infinite-Horizon Optimal Control Problems
    Nobusumi Sagara
    Set-Valued and Variational Analysis, 2010, 18 : 233 - 233
  • [18] Minimising conservatism in infinite-horizon LQR control
    Marjanovic, O
    Lennox, B
    Goulding, P
    Sandoz, D
    SYSTEMS & CONTROL LETTERS, 2002, 46 (04) : 271 - 279
  • [19] Conjugate points in infinite-horizon control problems
    Blot, J
    Hayek, N
    AUTOMATICA, 2001, 37 (04) : 523 - 526
  • [20] Infinite-horizon stable control of a parabolic equation
    M. S. Blizorukova
    Computational Mathematics and Mathematical Physics, 2015, 55 : 1461 - 1467