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
  • [41] Infinite horizon model predictive control for tracking problems
    Li, G
    Lennox, B
    Ding, ZT
    2005 International Conference on Control and Automation (ICCA), Vols 1 and 2, 2005, : 516 - 521
  • [42] Infinite horizon model predictive control with no terminal constraint
    Marjanovic, O
    Lennox, B
    COMPUTERS & CHEMICAL ENGINEERING, 2004, 28 (12) : 2605 - 2610
  • [43] Approximation of the infinite-horizon value function of the switched LQR problem
    Hou, Tan
    Li, Yuanlong
    Lin, Zongli
    AUTOMATICA, 2024, 159
  • [44] Stability of infinite-horizon optimal control with discounted cost
    Postoyan, R.
    Busoniu, L.
    Nesic, D.
    Daafouz, J.
    2014 IEEE 53RD ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2014, : 3903 - 3908
  • [45] Approximate Infinite-Horizon Optimal Control for Stochastic Systems
    Scarciotti, Giordano
    Mylvaganam, Thulasi
    2018 IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2018, : 3294 - 3298
  • [46] Infinite-horizon optimal control problems for nonlinear systems
    Sassano, M.
    Mylvaganam, T.
    Astolfi, A.
    2021 60TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2021, : 1721 - 1741
  • [47] PERTURBED INFINITE-HORIZON OPTIMAL-CONTROL PROBLEMS
    YE, JJ
    JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 1994, 182 (01) : 90 - 112
  • [48] COMPUTATIONAL ISSUES IN AN INFINITE-HORIZON, MULTIECHELON INVENTORY MODEL
    FEDERGRUEN, A
    ZIPKIN, P
    OPERATIONS RESEARCH, 1984, 32 (04) : 818 - 836
  • [49] Infinite-Horizon Gaussian Processes
    Solin, Arno
    Hensman, James
    Turner, Richard E.
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [50] INFINITE-HORIZON INCOMPLETE MARKETS
    MAGILL, M
    QUINZII, M
    ECONOMETRICA, 1994, 62 (04) : 853 - 880