From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Vahidi-Moghaddam, Amin, Boroujeni, Sayed Pedram Haeri, Jebellat, Iman, Jebellat, Ehsan, Mehrabi, Niloufar, Li, Zhaojian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909825530593280
author Vahidi-Moghaddam, Amin
Boroujeni, Sayed Pedram Haeri
Jebellat, Iman
Jebellat, Ehsan
Mehrabi, Niloufar
Li, Zhaojian
author_facet Vahidi-Moghaddam, Amin
Boroujeni, Sayed Pedram Haeri
Jebellat, Iman
Jebellat, Ehsan
Mehrabi, Niloufar
Li, Zhaojian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_04076
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents
Vahidi-Moghaddam, Amin
Boroujeni, Sayed Pedram Haeri
Jebellat, Iman
Jebellat, Ehsan
Mehrabi, Niloufar
Li, Zhaojian
Robotics
Systems and Control
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.
title From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents
topic Robotics
Systems and Control
url https://arxiv.org/abs/2510.04076