English
Related papers

Related papers: OCCAM: Online Continuous Controller Adaptation wit…

200 papers

A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed "meta" algorithms that convert any online learning algorithm to one that is adaptive to changing…

Machine Learning · Statistics 2017-11-08 Kwang-Sung Jun , Francesco Orabona , Stephen Wright , Rebecca Willett

We consider the online control problem with an unknown linear dynamical system in the presence of adversarial perturbations and adversarial convex loss functions. Although the problem is widely studied in model-based control, it remains…

Systems and Control · Electrical Eng. & Systems 2024-03-12 Zishun Liu , Yongxin Chen

We present an integrated approach for perception and control for an autonomous vehicle and demonstrate this approach in a high-fidelity urban driving simulator. Our approach first builds a model for the environment, then trains a policy…

Systems and Control · Electrical Eng. & Systems 2020-03-19 Ali Baheri , Ilya Kolmanovsky , Anouck Girard , H. Eric Tseng , Dimitar Filev

Robust control is a core approach for controlling systems with performance guarantees that are robust to modeling error, and is widely used in real-world systems. However, current robust control approaches can only handle small system…

Optimization and Control · Mathematics 2021-06-08 Dimitar Ho , Hoang M. Le , John C. Doyle , Yisong Yue

Autonomous robots must go from zero prior knowledge to safe control within seconds to operate in unstructured environments. Abrupt terrain changes, such as a sudden transition to ice, create dynamics shifts that can destabilize planners…

Robotics · Computer Science 2026-04-22 William Ward , Sarah Etter , Jesse Quattrociocchi , Christian Ellis , Adam J. Thorpe , Ufuk Topcu

One of the main features of adaptive systems is an oscillatory convergence that exacerbates with the speed of adaptation. Recently it has been shown that Closed-loop Reference Models (CRMs) can result in improved transient performance over…

Systems and Control · Computer Science 2013-10-04 Travis E. Gibson , Anuradha M. Annaswamy , Eugene Lavretsky

This text presents an introduction to an emerging paradigm in control of dynamical systems and differentiable reinforcement learning called online nonstochastic control. The new approach applies techniques from online convex optimization…

Machine Learning · Computer Science 2026-04-28 Elad Hazan , Karan Singh

This paper proposes a Safe Online Control-Informed Learning framework for safety-critical autonomous systems. The framework unifies optimal control, parameter estimation, and safety constraints into an online learning process. It employs an…

Systems and Control · Electrical Eng. & Systems 2025-12-25 Tianyu Zhou , Zihao Liang , Zehui Lu , Shaoshuai Mou

Learning quickly is of great importance for machine intelligence deployed in online platforms. With the capability of transferring knowledge from learned tasks, meta-learning has shown its effectiveness in online scenarios by continuously…

Machine Learning · Computer Science 2020-10-23 Huaxiu Yao , Yingbo Zhou , Mehrdad Mahdavi , Zhenhui Li , Richard Socher , Caiming Xiong

Model predictive control (MPC) has established itself as the primary methodology for constrained control, enabling general-purpose robot autonomy in diverse real-world scenarios. However, for most problems of interest, MPC relies on the…

Accurate prediction of human movements is required to enhance the efficiency of physical human-robot interaction. Behavioral differences across various users are crucial factors that limit the prediction of human motion. Although recent…

Robotics · Computer Science 2021-10-12 Hee-Seung Moon , Jiwon Seo

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study…

Robotics · Computer Science 2026-03-02 Shingo Ayabe , Hiroshi Kera , Kazuhiko Kawamoto

Robotic applications require the integration of various modalities, encompassing perception, control of real robots and possibly the control of simulated environments. While the state-of-the-art robotic software solutions such as ROS 2…

Robotics · Computer Science 2023-06-19 Vincent Berenz , Felix Widmaier , Simon Guist , Bernhard Schölkopf , Dieter Büchler

Domain adaptation is a sub-field of machine learning that involves transferring knowledge from a source domain to perform the same task in the target domain. It is a typical challenge in machine learning that arises, e.g., when data is…

Machine Learning · Computer Science 2025-01-09 Philipp Spitzer , Dominik Martin , Laurin Eichberger , Niklas Kühl

Adaptive filtering algorithms are pervasive throughout signal processing and have had a material impact on a wide variety of domains including audio processing, telecommunications, biomedical sensing, astrophysics and cosmology, seismology,…

Sound · Computer Science 2022-11-23 Jonah Casebeer , Nicholas J. Bryan , Paris Smaragdis

Batch training of machine learning models based on neural networks is now well established, whereas to date streaming methods are largely based on linear models. To go beyond linear in the online setting, nonparametric methods are of…

Signal Processing · Electrical Eng. & Systems 2020-01-22 Alec Koppel , Amrit Singh Bedi , Ketan Rajawat , Brian M. Sadler

When adopting a deep learning model for embodied agents, it is required that the model structure be optimized for specific tasks and operational conditions. Such optimization can be static such as model compression or dynamic such as…

Machine Learning · Computer Science 2024-06-18 Jaehyun Song , Minjong Yoo , Honguk Woo

The design (shape) of a robot is usually decided before the control is implemented. This might limit how well the design is adapted to a task, as the suitability of the design is given by how well the robot performs in the task, which…

Robotics · Computer Science 2025-09-30 Etor Arza , Frank Veenstra , Tønnes F. Nygaard , Kyrre Glette

In this paper we introduce a novel framework for expressing and learning force-sensitive robot manipulation skills. It is based on a formalism that extends our previous work on adaptive impedance control with meta parameter learning and…

Robotics · Computer Science 2018-05-23 Lars Johannsmeier , Malkin Gerchow , Sami Haddadin

Interactive applications incorporating high-data rate sensing and computer vision are becoming possible due to novel runtime systems and the use of parallel computation resources. To allow interactive use, such applications require careful…

Machine Learning · Computer Science 2012-03-19 Qian Zhu , Branislav Kveton , Lily Mummert , Padmanabhan Pillai