检索结果-内蒙古大学图书馆

Variable-Frequency model learning and Predictive control for Jumping Maneuvers on Legged Robots

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第2期10卷 1321-1328页

作者： Nguyen, Chuong Altawaitan, Abdullah Duong, Thai Atanasov, Nikolay Nguyen, Quan Univ Southern Calif Dept Aerosp & Mech Engn Los Angeles CA 90007 USA Univ Calif San Diego Dept Elect & Comp Engn La Jolla CA 92093 USA Kuwait Univ Safat 13060 Kuwait

Achieving both target accuracy and robustness in dynamic maneuvers with long flight phases, such as high or long jumps, has been a significant challenge for legged robots. To address this challenge, we propose a novel learning-based control approach consisting of model learning and model predictive control (MPC) utilizing a variable-frequency scheme. Compared to existing MPC techniques, we learn a model directly from experiments, accounting not only for leg dynamics but also for modeling errors and unknown dynamics mismatch in hardware and during contact. Additionally, learning the model with variable-frequency allows us to cover the entire flight phase and final jumping target, enhancing the prediction accuracy of the jumping trajectory. Using the learned model, we also design variable-frequency to effectively leverage different jumping phases and track the target accurately. In a total of 92 jumps on Unitree A1 robot hardware, we verify that our approach outperforms other MPCs using fixed-frequency or nominal model, reducing the jumping distance error $2-8$ times. We also achieve jumping distance errors of less than 3% during continuous jumping on uneven terrain with randomly-placed perturbations of random heights (up to 4 cm or 27% the robot's standing height). Our approach obtains distance errors of $1-2$ cm on 34 single and continuous jumps with different jumping targets and model uncertainties.

关键词： Robots Accuracy Legged locomotion Predictive models Robustness Hardware Aerodynamics Uncertainty Load modeling Real-time systems model learning for control legged robots whole-body motion planning and control

来源：评论

学校读者我要写书评

暂无评论

SOLAR-GP: Sparse Online Locally Adaptive Regression Using Gaussian Processes for Bayesian Robot model learning and control

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 2832-2839页

作者： Wilcox, Brian Yip, Michael C. Univ Calif San Diego Dept Elect & Comp Engn La Jolla CA 92093 USA

Machine learning methods have been widely used in robot control to learn inverse mappings. These methods are used to capture the entire non-linearities and non-idealities of a system that make geometric or phenomenological modeling difficult. Most methods employ some form of off-line or batch learning where training may be performed prior to a task, or in an intermittent manner, respectively. These strategies are generally unsuitable for teleoperation, where commands and sensor data are received in sequential streams and models must be learned on-the-fly. We combine sparse, local, and streaming methods to form Sparse Online Locally Adaptive Regression using Gaussian Processes (SOLAR-GP), which trains streaming data on localized sparse Gaussian Process models and infers a weighted local function mapping of the robot sensor states to joint states. The resultant prediction of the teleoperation command is used for joint control. The algorithm was adapted to perform on arbitrary link manipulators including the Baxter robot, where modifications to the algorithm are made to run training and prediction in parallel so as to keep consistent, high-frequency control loop rates. This framework allows for a user-defined cap on complexity of generated local models while retaining information on older regions of the explored state-space.

关键词： model learning for control learning and adaptive systems neural and fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Delayed Dynamic model Scheduled Reinforcement learning With Time-Varying Delays for Robotic control

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第3期10卷 2646-2653页

作者： Wang, Zechang Xing, Dengpeng Yang, Yiming Wang, Peng Univ Chinese Acad Sci Beijing 101408 Peoples R China Chinese Acad Sci Inst Automat Beijing 100045 Peoples R China

Reinforcement learning (RL) typically presupposes instantaneous agent-environment interactions, but in real-world scenarios such as robotic control, overlooking observation delays can significantly impair performance. While existing studies consider stationary, known delays, real-world applications frequently encounter unpredictable delay variations. To address this problem, this letter presents a novel algorithm for scheduling delayed dynamic models. Specifically, We propose using multiple truncated delay distributions to effectively model time-varying delays, with each distribution tailored to learn a specific delayed dynamic model. These models map delayed observations and historical actions to the current state, integrating seamlessly with existing RL algorithms to facilitate optimal decision-making. Since the delay is unknown to the agent, we propose an effective delay estimation method to detect delay and their corresponding distributions in real-time, thereby adaptively selecting the most appropriate delayed dynamic model to manage delays. To reduce instability caused by abrupt changes in delay distribution and enhance responsiveness to such variations, we apply Bayesian online changepoint detection to enable rapid sensing of alterations in the delay distribution within a finite number of time-steps. To the best of our knowledge, our approach is the first effective solution to the non-stationary time-varying delay problem in RL. Empirical results demonstrate the robust performance of our method in scenarios characterized by non-stationary observation delays, highlighting its strong potential for robotic control applications.

关键词： Delays Robots Heuristic algorithms Markov decision processes Gaussian distribution Dynamic scheduling Delay estimation Switches Probability density function Mathematical models model learning for control reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Active learning of Discrete-Time Dynamics for Uncertainty-Aware model Predictive control

引用

IEEE TRANSACTIONS ON ROBOTICS 2024年 40卷 1273-1291页

作者： Saviolo, Alessandro Frey, Jonathan Rathod, Abhishek Diehl, Moritz Loianno, Giuseppe NYU Tandon Sch Engn New York NY 11201 USA Univ Freiburg D-79110 Freiburg Germany

model-based control requires an accurate model of the system dynamics for precisely and safely controlling the robot in complex and dynamic environments. Moreover, in presence of variations in the operating conditions, the model should be continuously refined to compensate for dynamics changes. In this article, we present a self-supervised learning approach that actively models the dynamics of nonlinear robotic systems. We combine offline learning from past experience and online learning from current robot interaction with the unknown environment. These two ingredients enable a highly sample-efficient and adaptive learning process, capable of accurately inferring model dynamics in real-time even in operating regimes that greatly differ from the training distribution. Moreover, we design an uncertainty-aware model predictive controller that is heuristically conditioned to the aleatoric (data) uncertainty of the learned dynamics. This controller actively chooses the optimal control actions that i) optimize the control performance, and ii) improve the efficiency of online learning sample collection. We demonstrate the effectiveness of our method through a series of challenging real-world experiments using a quadrotor system. Our approach showcases high resilience and generalization capabilities by consistently adapting to unseen flight conditions, while it significantly outperforms classical and adaptive control baselines.

关键词： Adaptation models Robots Data models Vehicle dynamics Uncertainty Training Aerodynamics model learning for control aerial systems mechanics and control learning and adaptive systems optimization and optimal control

来源：评论

学校读者我要写书评

暂无评论

learning-Based Force control of Twisted String Actuators Using a Neural Network-Based Inverse model

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第9期9卷 8170-8177页

作者： Kwon, Hyeokjun Kim, Sung-Woo Joe, Hyun-Min Kyungpook Natl Univ Dept Robot & Smart Syst Engn Daegu 41566 South Korea Samsung Elect Robot Ctr Samsung Res Seoul 06765 South Korea

In this letter, we propose learning-based force control of twisted string actuators (TSAs) using a neural network-based inverse model. A learning-based force controller is designed using the input and output data of TSAs without a dynamic model of TSAs. Furthermore, the neural network-based inverse model is utilized to reduce model errors and handle nonlinearities between the inputs and outputs of the TSAs. The trained neural network-based inverse model is directly implemented as a force controller for the TSAs. Additionally, we propose data collection methods utilizing three types of inputs to improve the performance of the proposed controller. To verify the improved performance resulting from the proposed data collection methods, we compared the performance of the learning-based force controller for each dataset in the TSA hardware. We then selected the dataset with the best performance among the proposed inputs through experiments. Additionally, to verify the performance of the learning-based force controller, a reference force tracking experiment was performed and compared with a proportional-integral-derivative (PID) controller and feedback linearization. The learning-based force controller utilizing the selected input-based dataset demonstrated higher force tracking performance than the other controllers. Consequently, the TSA's learning-based force control demonstrates robust force control performance.

关键词： Force control machine learning for robot control data sets for robot learning model learning for control twisted string actuator (TSA) machine learning for robot control data sets for robot learning model learning for control twisted string actuator (TSA)

来源：评论

学校读者我要写书评

暂无评论

Real-Time Neural MPC: Deep learning model Predictive control for Quadrotors and Agile Robotic Platforms

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2023年第4期8卷 2397-2404页

作者： Salzmann, Tim Kaufmann, Elia Arrizabalaga, Jon Pavone, Marco Scaramuzza, Davide Ryll, Markus Tech Univ Munich D-85521 Munich Germany Univ Zurich CH-8050 Zurich Switzerland Stanford Univ Stanford CA 94305 USA NVIDIA Res Stanford CA 94305 USA Tech Univ Munich D-85521 Munich Germany Munich Inst Robot & Machine Intelligence MIRMI D-80992 Munich Germany

model Predictive control (MPC) has become a popular framework in embedded control for high-performance autonomous systems. However, to achieve good control performance using MPC, an accurate dynamics model is key. To maintain real-time operation, the dynamics models used on embedded systems have been limited to simple first-principle models, which substantially limits their representative power. In contrast to such simple models, machine learning approaches, specifically neural networks, have been shown to accurately model even complex dynamic effects, but their large computational complexity hindered combination with fast real-time iteration loops. With this work, we present Real-time Neural MPC, a framework to efficiently integrate large, complex neural network architectures as dynamics models within a model-predictive control pipeline. Our experiments, performed in simulation and the real world onboard a highly agile quadrotor platform, demonstrate the capabilities of the described system to run learned models with, previously infeasible, large modeling capacity using gradient-based online optimization MPC. Compared to prior implementations of neural networks in online optimization MPC we can leverage models of over 4000 times larger parametric capacity in a 50 Hz real-time window on an embedded platform. Further, we show the feasibility of our framework on real-world problems by reducing the positional tracking error by up to 82% when compared to state-of-the-art MPC approaches without neural network dynamics.

关键词： Machine learning for robot control model learning for control aerial systems Mechanics and control

来源：评论

学校读者我要写书评

暂无评论

A model Predictive control Approach for USV Autonomous Cruising via Disturbance learning 18

A Model Predictive Control Approach for USV Autonomous Cruis...

引用

IEEE 18th International Conference on control and Automation (ICCA)

作者： Cheng, Maotong Yao, Jinke Ren, Qinyuan Zhejiang Univ Control Sci & Engn Hangzhou Peoples R China

ISBN: (纸本)9798350354416;9798350354409

Unmanned surface vehicles (USVs) are widely applied in ocean exploration and environmental protection. To ensure efficient execution of tasks, the motion control of USV is essential and critical. However, the hydrodynamics disturbances from ocean environment are commonly highly nonlinear, time-variant and impractical to be modelled, which renders control extremely challenging. Therefore, in this paper we propose a learning-based model predictive control (MPC) approach for USV course-keeping subject to disturbances and uncertainties. A relatively simplified dynamics model is augmented by a long short term memory (LSTM) residual model, which can capture complicated hydrodynamics effect and eliminate model mismatch. The resulting formulation is incorporated in MPC framework to achieve optimal real-time control. Further, the proposed approach is verified through simulation experiments.

关键词： unmanned surface vehicle (USV) model learning for control model predictive control (MPC) autonomous cruising

来源：评论

学校读者我要写书评

暂无评论

Nonlinear model learning for Compensation and Feedforward control of Real-World Hydraulic Actuators Using Gaussian Processes

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第4期7卷 9525-9532页

作者： Taheri, Abdolreza Gustafsson, Pelle Rosth, Marcus Ghabcheloo, Reza Pajarinen, Joni HIAB Control Syst R&D S-82450 Hudiksvall Sweden Tampere Univ Fac Engn & Nat Sci Tampere 33100 Finland Aalto Univ Dept Elect Engn & Automat Espoo 02150 Finland Tech Univ Darmstadt Intelligent Autonomous Syst D-64289 Darmstadt Germany

This paper presents a robust machine learning framework for modeling and control of hydraulic actuators. We identify several important challenges concerning learning accurate models of the dynamics for real machines, including noise and uncertainty in state measurements, nonlinear effects, input delays, and data-efficiency. In particular, we propose a dual-Gaussian process (GP) model architecture to learn a surrogate dynamics model of the actuator, and showcase the accuracy of predictions against the piecewise and neural network models that have been widely used in the literature. In addition, we provide robust techniques for learning neural network inverse models and controllers by batch GP inference in an automated, seamless and computationally fast manner. Finally, we demonstrate the performance of the trained controllers in real-world feedforward and tracking control applications.

关键词： Hydraulic actuators machine learning for robot control model learning for control

来源：评论

学校读者我要写书评

暂无评论

learning-Based model Predictive control for Autonomous Racing

引用

WORLD ELECTRIC VEHICLE JOURNAL 2023年第7期14卷 163页

作者： Pinho, Joao Costa, Gabriel Lima, Pedro U. U. Ayala Botto, Miguel Univ Lisbon Inst Super Tecn Ave Rovisco Pais 1 P-1049001 Lisbon Portugal Univ Lisbon IDMEC Inst Super Tecn Ave Rovisco Pais 1 P-1049001 Lisbon Portugal

In this paper, we present the adaptation of the terminal component learning-based model predictive control (TC-LMPC) architecture for autonomous racing to the Formula Student Driverless (FSD) context. We test the TC-LMPC architecture, a reference-free controller that is able to learn from previous iterations by building an appropriate terminal safe set and terminal cost from collected trajectories and input sequences, in a vehicle simulator dedicated to the FSD competition. One major problem in autonomous racing is the difficulty in obtaining accurate highly nonlinear vehicle models that cover the entire performance envelope. This is more severe as the controller pushes for incrementally more aggressive behavior. To address this problem, we use offline and online measurements and machine learning (ML) techniques for the online adaptation of the vehicle model. We test two sparse Gaussian process regression (GPR) approximations for model learning. The novelty in the model learning segment is the use of a selection method for the initial training dataset that maximizes the information gain criterion. The TC-LMPC with model learning achieves a 5.9 s reduction (3%) in the total 10-lap FSD race time.

关键词： electric vehicle model predictive control learning-based control model learning for control Gaussian processes motion and path planning autonomous racing Formula Student

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic model-Based Online learning Optimal control Algorithm for Soft Pneumatic Actuators

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 1437-1444页

作者： Tang, Zhi Qiang Heung, Ho Lam Tong, Kai Yu Li, Zheng Chinese Univ Hong Kong Dept Biomed Engn Hong Kong Peoples R China Chinese Univ Hong Kong Dept Surg Hong Kong Peoples R China Chinese Univ Hong Kong Chow Yuk Ho Technol Ctr Innovat Med Hong Kong Peoples R China

Soft robots are increasingly being employed in different fields and various designs are created to satisfy relevant requirements. The wide ranges of design bring challenges to soft robotic control in that a unified control framework is difficult to derive. Traditional model-driven approaches for soft robots are usually design-specific which highly depend on specific design structures. Our approach to such challenges involves a probabilistic model that learns a mapping from the soft actuator states and controls to the next states. Then an optimal control policy is derived by minimizing a cost function based on the probabilistic model. We demonstrate the efficiency of our approach through simulations with parameter analysis and real-robot experiments involving three different designs of soft pneumatic actuators. Comparisons with previous model-based controllers are also provided to show advantages of the proposed method. Overall, this work provides a promising design-independent control approach for the soft robotics community.

关键词： modeling control and learning for soft robots model learning for control optimization and optimal control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：