Annual Review of Control, Robotics, and Autonomous Systems

Recent successes in the field of machine learning, as well as the availability of increased sensing and computational capabilities in modern control systems, have led to a growing interest in learning and data-driven control techniques. Model predictive control (MPC), as the prime methodology for constrained control, offers a significant opportunity to exploit the abundance of data in a reliable manner, particularly while taking safety constraints into account. This review aims at summarizing and categorizing previous research on learning-based MPC, i.e., the integration or combination of MPC with learning methods, for which we consider three main categories. Most of the research addresses learning for automatic improvement of the prediction model from recorded data. There is, however, also an increasing interest in techniques to infer the parameterization of the MPC controller, i.e., the cost and constraints, that lead to the best closed-loop performance. Finally, we discuss concepts that leverage MPC to augment learning-based controllers with constraint satisfaction properties.

Lukas Hewing

Kim P. Wabersich

Marcel Menner

Melanie N. Zeilinger

Annu. Rev. Control Robot. Auton. Syst.

Learning-Based Model Predictive Control: Toward Safe Learning in Control

基于学习的模型预测控制：迈向控制中的安全学习

In this review, we provide an overview of emerging trends and challenges in the field of intelligent and autonomous, or self-driving, vehicles. Recent advances in the field of perception, planning, and decision-making for autonomous vehicles have led to great improvements in functional capabilities, with several prototypes already driving on our roads and streets. Yet challenges remain regarding guaranteed performance and safety under all driving circumstances. For instance, planning methods that provide safe and system-compliant performance in complex, cluttered environments while modeling the uncertain interaction with other traffic participants are required. Furthermore, new paradigms, such as interactive planning and end-to-end learning, open up questions regarding safety and reliability that need to be addressed. In this survey, we emphasize recent approaches for integrated perception and planning and for behavior-aware planning, many of which rely on machine learning. This raises the question of verification and safety, which we also touch upon. Finally, we discuss the state of the art and remaining challenges for managing fleets of autonomous vehicles.

Wilko Schwarting

Javier Alonso-Mora

Daniela Rus

Planning and Decision-Making for Autonomous Vehicles

自动驾驶车辆的规划与决策

This article provides an introduction and overview of the inerter concept and device. Careful attention is given to the distinction between the inerter as an ideal modeling element and devices that approximate the ideal behavior. The background is given to the formal definition of the inerter as a mechanical one-port with terminal forces proportional to the relative acceleration between them. Four major methods of construction are described and modeled. The discussion focuses particularly on the notion of terminals, the distinction between a device and an effect, sign reversals, back driving in geared systems, the conceptual aspects of the modeling step for inerter embodiments, and the problem of reverse engineering to discover a purpose. The article includes an analysis and discussion of the rotational inerter, a brief review of the ideas of passive network synthesis that led to the inerter concept, and an analysis and discussion of several examples of integrated mechanical devices. It concludes with an imaginary dialogue between the author and an interlocutor on the understanding and purpose of the inerter.

Malcolm C. Smith

Annual Review of Control Robotics and Autonomous Systems

The Inerter: A Retrospective

惯性元件：回顾

The ability of a robot to build a persistent, accurate, and actionable model of its surroundings through sensor data in a timely manner is crucial for autonomous operation. While representing the world as a point cloud might be sufficient for localization, denser scene representations are required for obstacle avoidance. On the other hand, higher-level semantic information is often crucial for breaking down the necessary steps to autonomously complete a complex task, such as cooking. So the looming question is, What is a suitable scene representation for the robotic task at hand? This survey provides a comprehensive review of key approaches and frameworks driving progress in the field of robotic spatial perception, with a particular focus on the historical evolution and current trends in representation. By categorizing scene modeling techniques into three main types—metric, metric–semantic, and metric–semantic–topological—we discuss how spatial perception frameworks are transitioning from building purely geometric models of the world to more advanced data structures incorporating higher-level concepts, such as the notion of object instances and places. Special emphasis is placed on approaches for real-time simultaneous localization and mapping, their integration with deep learning for enhanced robustness and scene understanding, and their ability to handle scene dynamicity as some of the hottest topics of interest driving robotics research today. We conclude with a discussion of ongoing challenges and future research directions in the quest to develop robust and scalable spatial perception systems suitable for long-term autonomy.

Ruben Mascaro

Margarita Chli

Scene Representations for Robotic Spatial Perception

机器人空间感知的场景表示

This article reviews two techniques that use delay for control: time-delay approaches to control problems (which initially may be free of delays) and the intentional insertion of delays into the feedback. We begin with a now widely used time-delay approach to sampled-data control. In networked control systems with communication constraints, this is the only method that accommodates transmission delays larger than the sampling intervals. We present a predictor-based design that enlarges the maximum allowable delay, which is important for practical implementations. We then discuss methods that use artificial delays via simple Lyapunov functionals that lead to feasible linear matrix inequalities for small delays and simple sampled-data implementations. Finally, we briefly present a new time-delay approach—this time to averaging. Unlike previous results, this approach provides the first quantitative bounds on the small parameter, making averaging-based control (including vibrational and extremum-seeking control) reliable.

Emilia Fridman

Anton Selivanov

Using Delay for Control

使用延迟进行控制

The limited bioavailability, susceptibility to degradation, and adverse side effects of novel drugs often hinder their effective administration. Nanoparticles, with customizable properties and small size, have emerged as potential carriers, though their delivery efficiency remains low. With their ability to navigate fluid environments, micro- and nanorobots offer promising solutions to improve the delivery and retention of drugs at targeted tissues. The design and composition of these motile devices, often inspired by natural locomotion mechanisms, are currently being refined for improved biocompatibility, adaptability, and collective task performance. Recent research has focused on loading these devices with therapeutic agents and evaluating their efficacy in living organisms. While chemotherapy has been predominant, micro- and nanorobots also show significant potential for biological and physical therapies, and hybrid methods combining multiple therapies have demonstrated synergistic benefits. This review identifies major challenges, including the need for application-specific solutions, standardized performance evaluation methods, and the integration of engineering with pharmacology.

Minsoo Kim

James D. Nicholas

Josep Puigmartí-Luis

Bradley J. Nelson

Salvador Pané

Targeted Drug Delivery: From Chemistry to Robotics at Small Scales

靶向药物递送：从小尺度化学到机器人技术

An ideal robot could autonomously complete diverse tasks such as ocean surveying, kitchen cleaning, and aerial environmental monitoring. However, robots optimized for each task typically have different shapes, posing a challenge in reconciling form and function. This challenge inspires the pursuit of general shape-changing robots (GSCRs). While soft materials and actuators are promising for GSCRs due to their ability to accommodate extreme deformations, there is a gap between the vision of GSCRs and the simple examples we see today. Two critical components are needed: robot-agnostic stretchable shape sensing and stretchable computing. Together, these components would enable closed-loop shape control and the first instantiations of GSCRs. This review aims to consolidate the literature on these components, encouraging researchers to bridge the gap between today's shape-changing robots and the envisioned GSCRs, ultimately advancing the field toward more versatile and adaptive robots.

Stephanie J. Woodman

Rebecca Kramer-Bottiglio

Stretchable Shape Sensing and Computation for General Shape-Changing Robots

通用形变机器人中的可拉伸形状感知与计算

The development of control methods based on data has seen a surge of interest in recent years. When applying data-driven controllers in real-world applications, providing theoretical guarantees for the closed-loop system is of crucial importance to ensure reliable operation. In this review, we provide an overview of data-driven model predictive control (MPC) methods for controlling unknown systems with guarantees on systems-theoretic properties such as stability, robustness, and constraint satisfaction. The considered approaches rely on the fundamental lemma from behavioral theory in order to predict input–output trajectories directly from data. We cover various setups, ranging from linear systems and noise-free data to more realistic formulations with noise and nonlinearities, and we provide an overview of different techniques to ensure guarantees for the closed-loop system. Moreover, we discuss avenues for future research that may further improve the theoretical understanding and practical applicability of data-driven MPC.

Julian Berberich

Frank Allgöwer

An Overview of Systems-Theoretic Guarantees in Data-Driven Model Predictive Control

数据驱动模型预测控制中基于系统理论的保证综述

短名	Annu. Rev. Control Robot. Auton. Syst.
Journal Impact	11.39
国际分区	ROBOTICS(Q1)
期刊索引	SCI Q1中科院 1 区

ISSN	2573-5144
h-index	36
国内分区	计算机科学(1区)计算机科学自动化与控制系统(1区)计算机科学机器人学(2区)

涉及主题	计算机科学人工智能数学工程类物理机器人生物经济管理机器人学量子力学程序设计语言控制（管理）人机交互统计操作系统地理哲学机器学习电气工程
出版信息	出版商: Annual Reviews Inc.，出版周期: ，期刊类型: journal，开源期刊: 否
基本数据	创刊年份: 2018，原创研究文献占比: 0.00%，自引率:0.00%， Gold OA占比: 30.99%

Annual Review of Control, Robotics, and Autonomous Systems

期刊引文格式

有 1 位以上作者的期刊

有 2 位作者的期刊

有 3 位作者的期刊

有 5 位以上作者的期刊

书籍引用格式

学位论文引用格式

网页引用格式

专利引用格式

手工熬夜修改参考文献？研飞自动匹配期刊，一键轻松成稿，支持 Word/WPS

投稿经验分享

Learning-Based Model Predictive Control: Toward Safe Learning in Control

Planning and Decision-Making for Autonomous Vehicles

The Inerter: A Retrospective

Scene Representations for Robotic Spatial Perception

Using Delay for Control

Using Delay for Control

Targeted Drug Delivery: From Chemistry to Robotics at Small Scales

Scene Representations for Robotic Spatial Perception

Stretchable Shape Sensing and Computation for General Shape-Changing Robots

An Overview of Systems-Theoretic Guarantees in Data-Driven Model Predictive Control