从阴影到光明：面向MPC、DeePC、RL和LLM智能体的安全高效策略学习
From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents
AI总结：
针对MPC、DeePC、RL、LLM等数据驱动控制策略计算与内存开销高、难适配快动态受限系统的问题，本文提出8种降复杂度方法，并在多类实际控制场景中验证了其安全高效的性能。
摘要：
现代控制应用（尤其是机器人与车辆运动控制）的核心挑战之一是实现精准、快速且安全的运动。为解决这一问题，研究人员已开发出最优控制策略，在保障高性能的同时落实安全约束。由于实际系统通常具备基础的第一性原理模型，基于模型的控制器得到了广泛应用。模型预测控制（MPC）是主流方法，可在优化性能的同时显式处理安全约束。但复杂系统的精准建模难度较大，这推动了数据驱动替代方案的发展。基于机器学习的MPC利用学习得到的模型降低对人工构建动力学模型的依赖，强化学习（RL）则可直接通过交互数据学习接近最优的策略。数据驱动预测控制（DeePC）更进一步，完全跳过建模环节，直接从原始输入输出数据中学习安全策略。近年来，大语言模型（LLM）智能体也应运而生，可将自然语言指令转化为最优控制问题的结构化表述。尽管取得了这些进展，数据驱动策略仍存在显著局限：它们通常响应速度慢、计算需求高、内存占用大，在动力学响应快、机载计算能力有限或内存约束严格的实际系统中实用性不足。为解决这一问题，学界已提出降阶建模、函数逼近策略学习、凸松弛等多种降低计算复杂度的技术。本文提出了8种此类方法，并在机械臂、软体机器人、车辆运动控制等实际应用场景中验证了其有效性。
英文摘要：
One of the main challenges in modern control applications, particularly in robot and vehicle motion control, is achieving accurate, fast, and safe movement. To address this, optimal control policies have been developed to enforce safety while ensuring high performance. Since basic first-principles models of real systems are often available, model-based controllers are widely used. Model predictive control (MPC) is a leading approach that optimizes performance while explicitly handling safety constraints. However, obtaining accurate models for complex systems is difficult, which motivates data-driven alternatives. ML-based MPC leverages learned models to reduce reliance on hand-crafted dynamics, while reinforcement learning (RL) can learn near-optimal policies directly from interaction data. Data-enabled predictive control (DeePC) goes further by bypassing modeling altogether, directly learning safe policies from raw input-output data. Recently, large language model (LLM) agents have also emerged, translating natural language instructions into structured formulations of optimal control problems. Despite these advances, data-driven policies face significant limitations. They often suffer from slow response times, high computational demands, and large memory needs, making them less practical for real-world systems with fast dynamics, limited onboard computing, or strict memory constraints. To address this, various technique, such as reduced-order modeling, function-approximated policy learning, and convex relaxations, have been proposed to reduce computational complexity. In this paper, we present eight such approaches and demonstrate their effectiveness across real-world applications, including robotic arms, soft robots, and vehicle motion control.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
