A Data-Driven Distributed Control Scheme: Learning Multi-Objective Agent-Based MPC for Path-Tracking

📄 arXiv: 2609.12142v1 📥 PDF

作者: Jiaming Zhong, Reza Valiollahi Mehrizi, Yash Vardhan Pant, Amir Khajepour

分类: cs.RO

发布日期: 2026-09-10

备注: 7 pages, 8 figures, 2 tables. Author accepted manuscript of a paper published in IEEE ITSC 2024

期刊: 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), Edmonton, AB, Canada, pp. 2999-3004, 2024

DOI: 10.1109/ITSC58415.2024.10919711


💡 一句话要点

提出学习多目标代理基础的MPC以解决路径跟踪问题

🎯 匹配领域: 支柱一:机器人控制 (Robot Control)

关键词: 模型预测控制 多目标优化 代理基础控制 路径跟踪 自动驾驶 实时系统 学习算法

📋 核心要点

  1. 现有的集成MPC方法在处理多个相互冲突的目标时,面临计算负担和维护困难等挑战。
  2. 本文提出了一种基于学习的多目标AMPC,通过信息交换解耦系统,提升设计灵活性和计算效率。
  3. 实验结果表明,所提方案在路径跟踪仿真中与集成方案性能相当,但计算时间减少了43.5%,学习方法更是节省了88.6%的计算时间。

📝 摘要(中文)

代理基础的模型预测控制(AMPC)最近被提出用于车辆系统,然而在处理多个相互冲突的目标时面临挑战。本文提出了一种学习多目标AMPC,旨在提高设计灵活性和计算效率。首先,基于信息交换的假设,提出了一种多目标AMPC,利用交替方向乘子法(ADMM)来解耦系统并实现与集成方案相同的性能。其次,提出了一种基于学习的方法来初始化迭代,以加速收敛。此外,提出了一种数据管理方法以提高实时效率,并设计了一个认证模块以确保学习的可靠性。通过对比实验,所提方案在路径跟踪仿真中实现了与集成方案相同的控制性能,同时计算时间减少了43.5%。

🔬 方法详解

问题定义:本文旨在解决在多目标代理基础的模型预测控制(AMPC)中,如何有效处理多个相互冲突的目标及其带来的计算负担和维护困难的问题。现有的集成MPC方法在目标和代理数量增加时,面临显著的计算挑战。

核心思路:论文提出了一种基于学习的多目标AMPC,通过信息交换和交替方向乘子法(ADMM)来解耦系统,逐步实现与集成方案相同的控制性能,同时提高计算效率。

技术框架:整体架构包括信息交换模块、基于ADMM的多目标控制模块、学习初始化模块和数据管理模块。信息交换模块确保各代理之间的信息共享,ADMM模块负责优化控制策略,学习模块加速收敛,而数据管理模块则提升实时处理能力。

关键创新:最重要的技术创新在于提出了一种学习初始化方法,显著加快了迭代收敛速度,并通过信息交换实现了系统的解耦,这与传统的集成MPC方法形成了鲜明对比。

关键设计:在设计中,采用了基于ADMM的优化算法,设置了适当的学习率和迭代次数,以确保收敛性和稳定性。同时,数据管理模块通过实时数据处理提升了系统的响应速度。该方法的设计考虑了实际应用中的实时性需求。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示,所提学习多目标AMPC方案在路径跟踪仿真中,控制性能与集成方案相当,但计算时间减少了43.5%。此外,基于学习的方法相比于无学习方法,节省了88.6%的计算时间,显示出显著的效率提升。

🎯 应用场景

该研究的潜在应用领域包括自动驾驶车辆的路径跟踪控制、智能交通系统以及多机器人协作等。通过提高控制系统的灵活性和计算效率,该方法能够在复杂环境中实现更高效的实时决策,具有重要的实际价值和广泛的应用前景。

📄 摘要(原文)

Agent-based model predictive control (AMPC) has recently been proposed for vehicle systems with various controllers, such as differential braking and torque vectoring, where controllers are regarded as distributed agents contributing to the same objective. However, this scheme is challenging in handling multiple conflicting objectives with coupled agents. A common approach for such tasks is the integrated MPC, where all objectives and agents are stacked together in one optimization. Nevertheless, as more agents and objectives are involved, the integrated MPC will face challenges like computational burdens and maintenance difficulties in practice. To this end, this paper proposes a learning multi-objective AMPC that can improve design flexibility and computing efficiency. First, under the assumption of information exchange, a multi-objective AMPC tailored from the alternating direction method of multipliers (ADMM) is proposed to decouple the system and achieve the same performance as the integrated scheme iteratively. Second, a learning-based method for initializing iterations is proposed to accelerate convergence. In addition, a data management method is proposed for real-time efficiency, and an authentication module is designed for learning reliability. We compare the proposed scheme against the integrated scheme via a combined path-tracking simulation for autonomous vehicles with various controllers. The proposed scheme achieves the same control performance as the integrated one while reducing the computational time by 43.5%. Furthermore, the learning-based method saves 88.6% more computational time than without learning, making it suitable for real-time implementation.