The Value of Planning for Infinite-Horizon Model Predictive Control

被引:5
|
作者
Hatch, Nathan
Boots, Byron
机构
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
  • [1] Approximate infinite-horizon predictive control
    Beckenbach, Lukas
    Streif, Stefan
    2022 IEEE 61ST CONFERENCE ON DECISION AND CONTROL (CDC), 2022, : 3711 - 3717
  • [2] Infinite-horizon model predictive control with structured input signals
    van den Boom, TJJ
    PROCEEDINGS OF THE 2002 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2002, 1-6 : 448 - 453
  • [3] Toward infinite-horizon optimality in nonlinear model predictive control
    Hu, B
    Linnemann, A
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2002, 47 (04) : 679 - 682
  • [4] Constrained Infinite-Horizon Model Predictive Control for Fuzzy-Discrete-Time Systems
    Xia, Yuanqing
    Yang, Hongjiu
    Shi, Peng
    Fu, Mengyin
    IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2010, 18 (02) : 429 - 436
  • [5] IGCC Power Plant Dispatch Using Infinite-Horizon Economic Model Predictive Control
    Omell, Benjamin P.
    Chmielewski, Donald J.
    INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2013, 52 (09) : 3151 - 3164
  • [6] Computationally efficient infinite-horizon indefinite model predictive control with disturbance preview information
    Zhan, Siyuan
    Chen, Wen-Hua
    Steffen, Thomas
    V. Ringwood, John
    AUTOMATICA, 2022, 146
  • [7] Approximation of Continuous-Time Infinite-Horizon Optimal Control Problems Arising in Model Predictive Control
    Muehlebach, Michael
    D'Andrea, Raffaello
    2016 IEEE 55TH CONFERENCE ON DECISION AND CONTROL (CDC), 2016, : 1464 - 1470
  • [8] PROBLEMS OF OPTIMAL INFINITE-HORIZON CONTROL
    PIUNOVSKIY, AB
    SOVIET JOURNAL OF COMPUTER AND SYSTEMS SCIENCES, 1990, 28 (06): : 65 - 71
  • [9] Comments on "Constrained Infinite-Horizon Model Predictive Control for Fuzzy-Discrete-Time Systems"
    Ding, Baocang
    IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2011, 19 (03) : 598 - 600
  • [10] Value Functions and Transversality Conditions for Infinite-Horizon Optimal Control Problems
    Sagara, Nobusumi
    SET-VALUED AND VARIATIONAL ANALYSIS, 2010, 18 (01) : 1 - 28