发表机构
Northwestern University; Idiap Research Institute; Carnegie Mellon University; University of Rijeka; National University of Singapore; Pennsylvania State University; University of Sydney; Yale University（西北大学; Idiap研究所; 卡内基梅隆大学; 里耶卡大学; 新加坡国立大学; 宾夕法尼亚州立大学; 悉尼大学; 耶鲁大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述介绍受控扩散与遍历控制的理论基础、数值教程及其在机器人学习中的应用，强调其通过强制统计最优性、非短视搜索和空间行为规范，区别于传统扩散学习，并展望未来挑战。
AI 中文摘要
扩散学习利用扩散过程的统计机制，从数据中学习、推理和推断复杂分布。近年来，扩散学习的进展具有变革性，机器人学习成为关键的应用领域，其应用涵盖感知、控制和决策。同时，扩散过程的统计机制可以被控制，以塑造机器人轨迹底层状态分布的时间演化，从而在机器人系统中诱发遍历行为。受控扩散和遍历控制的框架与扩散学习大约在同一时期发展起来，它们的理论和算法已日益趋同。由受控扩散诱发的遍历性对机器人学习具有若干重要意义，这不同于将扩散学习应用于机器人问题：它正式强制实施确保机器人学习最优性所需的统计特性，能够在不确定信息景观上进行非短视搜索以进行数据收集，并能够基于轨迹的空间而非时间特征进行行为规范。本综述介绍了受控扩散用于机器人学习的直觉，探讨了其与扩散学习的联系，提供了求解受控扩散和遍历控制问题的理论基础和数值教程，并回顾了机器人领域的应用。最后，我们讨论了利用受控扩散进行机器人学习的关键挑战和未来机遇。
英文摘要
Diffusion learning leverages the statistical mechanism of diffusion processes for learning, reasoning, and inferring complex distributions from data. Recent advances in diffusion learning have been transformative, with robot learning emerging as a key opportunity area, with applications spanning perception, control, and decision-making. At the same time, the statistical mechanism of diffusion processes can be controlled to shape the temporal evolution of the state distribution underlying robot trajectories, inducing ergodic behavior in robotic systems. The frameworks of controlled diffusion and ergodic control were developed around the same time as diffusion learning, and their theories and algorithms have increasingly converged. Ergodicity induced by controlled diffusion has several significant implications for robot learning, distinct from applying diffusion learning to robotics problems: it formally enforces statistical properties required to ensure optimality of robot learning, enables non-myopic search over uncertain information landscapes for data collection, and enables behavior specification based on spatial rather than temporal characteristics of trajectories. This survey introduces the intuition behind controlled diffusion for robot learning, explores its connection to diffusion learning, presents theoretical foundations and numerical tutorials for solving controlled diffusion and ergodic control problems, and reviews applications across robotics. Finally, we discuss key challenges and future opportunities in leveraging controlled diffusion for robot learning.
CommentsUnder review at Foundations and Trends in Robotics
