机器人学习中的物理先验嵌入：综述

中文摘要 AI 辅助

人工智能的快速发展正在重塑机器人学，并加速了基于学习方法的应用。尽管纯数据驱动的方法在计算机视觉和自然语言处理领域取得了显著成功，但机器人学仍受限于数据有限、复杂的现实世界交互以及对可靠运行的需求。这些挑战促使了对物理嵌入机器人学习（physics-embedded robot learning）的探索，该方法将物理先验嵌入学习算法中。通过编码潜在的物理定律和约束，物理先验可以用机器人特有的归纳偏置来补充有限的数据，从而可能提高泛化能力、可解释性和样本效率。然而，关于物理嵌入机器人学习的文献在术语、方法和应用领域上仍然分散，使得评估这一不断增长的研究领域变得困难。本综述回顾了物理嵌入机器人学习在广泛的物理先验、机器人应用和机器学习模型（从单层感知机到生成式基础模型）中的研究。我们采用了一个统一的分类法，根据物理嵌入方式对现有方法进行分类：物理引导的输入、数据和表示；物理编码的模型架构；以及物理信息驱动的训练损失函数。基于这一分类法，我们回顾了机器人动力学学习、轨迹规划、预测、控制和估计的方法，以及相应的开源软件生态系统。我们指出了关键开放挑战，并概述了有前景的未来研究方向。总体而言，我们认为物理先验提供了一种特别相关的机器人特有归纳偏置，补充而非取代数据驱动学习，并为更可泛化、数据高效和可信赖的机器人系统铺平道路。

英文摘要

The rapid progress of artificial intelligence is reshaping robotics and accelerating the adoption of learning-based approaches. While purely data-driven methods have achieved remarkable success in computer vision and natural language processing, robotics remains constrained by limited data, complex real-world interactions, and the need for reliable operation. These challenges have motivated the exploration of physics-embedded robot learning, which embeds physics priors into learning algorithms. By encoding the underlying physical laws and constraints, physics priors can complement limited data with robotics-specific inductive biases, potentially improving generalization, interpretability, and sample efficiency. However, the literature on physics-embedded robot learning remains fragmented across terminology, methodologies, and application domains, making it difficult to assess this growing body of work. This survey reviews physics-embedded robot learning across a broad range of physics priors, robotics applications, and machine learning models, from single-layer perceptrons to generative foundation models. We adopt a unified taxonomy that classifies existing approaches according to their physics embedding: physics-guided inputs, data, and representations; physics-encoded model architectures; and physics-informed training loss functions. Building on this taxonomy, we review methods for robot dynamics learning, trajectory planning, prediction, control, and estimation, together with the corresponding open-source software ecosystem. We identify key open challenges, and outline promising future research directions. Overall, we argue that physics priors provide a particularly relevant robotics-specific inductive bias, complementing rather than replacing data-driven learning, and paving the way toward more generalizable, data-efficient, and trustworthy robotic systems.

发表机构

• Technical University of Munich（慕尼黑工业大学）
• Technical University of Darmstadt（达姆施塔特工业大学）
• University of Trento（特伦托大学）
• Ulm University（乌尔姆大学）

机构由 AI 辅助整理，请以论文原文为准。