检索结果-内蒙古大学图书馆

Hydrodynamic modeling of a robotic surface vehicle using representation learning for long-term prediction

OCEAN ENGINEERING 2023年第1期270卷

作者： Jang, Junwoo Kim, Jinwhan Korea Adv Inst Sci & Technol Dept Mech Engn Daejeon 34141 South Korea

The hydrodynamic modeling of a surface vehicle in an aquatic environment is known to be a challenging problem. In particular, it is difficult to calculate the hydrodynamic forces due to the intricate coupling of the vehicle with water. In recent years, deep dynamics models have been utilized to improve the accuracy of dynamics modeling precision. However, it is well known that data-driven approaches do not extrapolate well and are vulnerable to out-of-distribution data. In this paper, we argue that the naive use of neural networks may reduce the accuracy of long-term predictions. In order to address this issue, we employ representation learning techniques that facilitate the learning of the valid data space, so that long-term predictions can be made within the valid data space. In addition, hallucinated replay is incorporated into the prediction network to further improve the accuracy of long-term predictions. We validate the proposed method on experimental data using a robotic surface vehicle and demonstrate its application to path tracking control.

关键词： Machine learning for modeling Marine robotics model learning for control

来源：评论

学校读者我要写书评

暂无评论

Guiding Robot model Construction with Prior Features

Guiding Robot Model Construction with Prior Features

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Derner, Erik Kubalik, Jiri Babuska, Robert Czech Tech Univ Czech Inst Informat Robot & Cybernet Prague 16000 Czech Republic Czech Tech Univ Fac Elect Engn Dept Control Engn Prague 12135 Czech Republic Delft Univ Technol Fac 3mE Cognit Robot NL-2628 CD Delft Netherlands

ISBN: (纸本)9781665417143

Virtually all robot control methods benefit from the availability of an accurate mathematical model of the robot. However, obtaining a sufficient amount of informative data for constructing dynamic models can be difficult, especially when the models are to be learned during robot deployment. Under such circumstances, standard data-driven model learning techniques often yield models that do not comply with the physics of the robot. We extend a symbolic regression algorithm based on Single Node Genetic Programming by including the prior model information into the model construction process. In this way, symbolic regression automatically builds models that compensate for theoretical or empirical model deficiencies. We experimentally demonstrate the approach on two real-world systems: the TurtleBot 2 mobile robot and the Parrot Bebop 2 drone. The results show that the proposed model-learning algorithm produces realistic models that fit well the training data even when using small training sets. Passing the prior model information to the algorithm significantly improves the model accuracy while speeding up the search.

关键词： model learning for control AI-based methods genetic programming prior knowledge

来源：评论

学校读者我要写书评

暂无评论

Online Simultaneous Semi-Parametric Dynamics model learning

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 2039-2046页

作者： Smith, Joshua Mistry, Michael Univ Edinburgh Sch Informat Edinburgh EH8 9YL Midlothian Scotland

Accurate models of robots dynamics are critical for control, stability, motion optimization, and interaction. Semi-Parametric approaches to dynamics learning combine physics-based Parametric models with unstructured Non-Parametric regression with the hope to achieve both accuracy and generalizability. In this letter, we highlight the non-stationary problem created when attempting to adapt both Parametric and Non-Parametric components simultaneously. We present a consistency transform designed to compensate for this non-stationary effect, such that the contributions of both models can adapt simultaneously without adversely affecting the performance of the platform. Thus, we are able to apply the Semi-Parametric learning approach for continuous iterative online adaptation, without relying on batch or offline updates. We validate the transform via a perfect virtual model as well as by applying the overall system on a Kuka LWR IV manipulator. We demonstrate improved tracking performance during online learning and show a clear transference of contribution between the two components with a learning bias towards the Parametric component.

关键词： Dynamics calibration and identification model learning for control robust adaptive control of robotic systems

来源：评论

学校读者我要写书评

暂无评论

Data-Efficient model learning and Prediction for Contact-Rich Manipulation Tasks

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第3期5卷 4321-4328页

作者： Khader, Shahbaz Abdul Yin, Hang Falco, Pietro Kragic, Danica KTH EECS RPL S-10044 Stockholm Sweden ABB Future Labs CH-5405 Baden Switzerland ABB Corp Res S-72178 Vasteras Sweden

In this letter, we investigate learning forward dynamics models and multi-step prediction of state variables (long-term prediction) for contact-rich manipulation. The problems are formulated in the context of model-based reinforcement learning (MBRL). We focus on two aspects-discontinuous dynamics and data-efficiency-both of which are important in the identified scope and pose significant challenges to State-of-the-Art methods. We contribute to closing this gap by proposing a method that explicitly adopts a specific hybrid structure for the model while leveraging the uncertainty representation and data-efficiency of Gaussian process. Our experiments on an illustrative moving block task and a 7-DOF robot demonstrate a clear advantage when compared to popular baselines in low data regimes.

关键词： model learning for control contact modeling reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Disturbance Observers for Estimating External Forces on Soft Robots

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第4期5卷 5717-5724页

作者： Santina, Cosimo Della Truby, Ryan Landon Rus, Daniela MIT Comp Sci & Artificial Intelligence Lab 77 Massachusetts Ave Cambridge MA 02139 USA

Unlike traditional robots, soft robots can intrinsically interact with their environment in a continuous, robust, and safe manner. These abilities - and the new opportunities they open - motivate the development of algorithms that provide reliable information on the nature of environmental interactions and, thereby, enable soft robots to reason on and properly react to external contact events. However, directly extracting such information with integrated sensors remains an arduous task that is further complicated by also needing to sense the soft robot's configuration. As an alternative to direct sensing, this paper addresses the challenge of estimating contact forces directly from the robot's posture. We propose a new technique that merges a nominal disturbance observer, a model-based component, with corrections learned from data. The result is an algorithm that is accurate yet sample efficient, and one that can reliably estimate external contact events with the environment. We prove the convergence of our proposed method analytically, and we demonstrate its performance with simulations and physical experiments.

关键词： modeling control and learning for soft robots contact modeling model learning for control

来源：评论

学校读者我要写书评

暂无评论

A Cerebellar Internal models control Architecture for Online Sensorimotor Adaptation of a Humanoid Robot Acting in a Dynamic Environment

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第1期5卷 80-87页

作者： Capolei, Marie Claire Andersen, Nils Axel Lund, Henrik Hautop Falotico, Egidio Tolu, Silvia Tech Univ Denmark Automat & Control Grp Dept Elect Engn DK-2800 Lyngby Denmark Scuola Super Sant Anna BioRobot Inst I-56025 Pontedera Italy

Humanoid robots are often supposed to operate in non-deterministic human environments, and as a consequence, the robust and gentle rejection of the external perturbations is extremely crucial. In this scenario, stable and accurate behavior is mostly solved through adaptive control mechanisms that learn an internal model to predict the consequences of the outgoing control signals. Evidences show that brain-based biological systems resolve this control issue by updating an appropriate internal model that is then used to direct the muscles activities. Inspired by the biological cerebellar internal models theory, that couples forward and inverse internal models into the biological motor control scheme, we propose a novel methodology to artificially replicate these learning and adaptive principles into a robotic feedback controller. The proposed cerebellar-like network combines machine learning, artificial neural network, and computational neuroscience techniques to deal with all the nonlinearities and complexities that modern robotic systems could present. Although the architecture is tested on the simulated humanoid iCub, it can be applied to different robotic systems without excessive customization, thanks to its neural network-based nature. During the experiments, the robot is requested to follow repeatedly a movement while it is interacting with two external systems. Four different internal model architectures are compared and tested under different conditions. The comparison of the performances confirmed the theories about internal models combinatory action. The combination of models together with the structural and learning features of the network, resulted in a benefit to the adaptation mechanism, but also the system response to nonlinearities, noise and external forces.

关键词： Adaptation models Robot sensing systems Computational modeling Computer architecture Brain modeling Adaptive control Biomimetics Neurorobotics model learning for control learning and adaptive systems control architectures and programming

来源：评论

学校读者我要写书评

暂无评论

External Force Estimation for Industrial Robots With Flexible Joints

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 1311-1318页

作者： Lin, Yang Zhao, Huan Ding, Han Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Sch Mech Sci & Engn Wuhan 430074 Hubei Peoples R China

With no force sensors, estimating forces for robotic manipulation has gained a lot of attention. However, for industrial robots with harmonic drives (flexible joints), deviations between joint and motor positions inevitably deteriorate the force estimation performance due to the lack of encoders on the joint side. To this end, this letter presents a method to estimate not only joint states but also external forces. The method includes an extended disturbance state observer (DSO) and a proposed task-oriented disturbance modeling (TDM). First, a robust DSO is extended to robots with flexible joints aiming to estimate joint states and disturbances. Then, due to the observed disturbances including (possibly) external forces and also uncertainties such as measurement noises and model errors of the robot dynamics, a learning part is proposed to model the task-oriented disturbances during no-contact motion aiming to improve the effect of uncertainties on the force estimation performance. Finally, when the robot comes in contact with the environment, external forces are estimated as the differences between the modeled (no-contact) disturbances and the real-time observed disturbances. Experimental results, obtained on a six-degrees-of-freedom (6-DOF) industrial robot with flexible joints, show the feasibility and effectiveness of the proposed method.

关键词： Force and tactile sensing model learning for control compliant joint dynamics industrial robots

来源：评论

学校读者我要写书评

暂无评论

Autonomous Excavation of Rocks Using a Gaussian Process model and Unscented Kalman Filter

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 2491-2497页

作者： Sotiropoulos, Filippos E. Asada, H. Harry MIT Dept Mech Engn Cambridge MA 02139 USA

In large-scale open-pit mining and construction works, excavators must deal with large rocks mixed with gravel and granular soil. Capturing and moving large rocks with the bucket of an excavator requires a high level of skill that only experienced human operators possess. In an attempt to develop autonomous rock excavators, this letter presents a control method that predicts the rock movement in response to bucket operation and computes an optimal bucket movement to capture the rock. The process is highly nonlinear and stochastic. A Gaussian process model, which is nonlinear, nonparametric, and stochastic, is used for describing rock behaviors interacting with the bucket and surrounding soil. Experimental data is used directly for identifying the model. An Unscented Kalman Filter (UKF) is then integrated with the Gaussian process model for predicting the rock movements and estimating the length of the rock. A feedback controller that optimizes a cost function is designed based on the rock motion prediction and implemented on a robotic excavator prototype. Experiments demonstrate encouraging results towards autonomous mining and rock excavation.

关键词： model learning for control mining robotics robotics in construction field robots robot manipulation autonomous excavation Gaussian process UKF data-driven control

来源：评论

学校读者我要写书评

暂无评论

A Data-Efficient Geometrically Inspired Polynomial Kernel for Robot Inverse Dynamic

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第1期5卷 24-31页

作者： Dalla Libera, Alberto Carli, Ruggero Univ Padua Dept Informat Engn I-35131 Padua Italy

In this letter, we introduce a novel data-driven inverse dynamics estimator based on Gaussian Process Regression. Driven by the fact that the inverse dynamics can be described as a polynomial function on a suitable input space, we propose the use of a novel kernel, called Geometrically Inspired Polynomial Kernel (GIP). The resulting estimator behaves similarly to model-based approaches as concerns data efficiency. Indeed, we proved that the GIP kernel defines a finite-dimensional Reproducing Kernel Hilbert Space that contains the inverse dynamics function computed through the Rigid Body Dynamics. The proposed kernel is based on the recently introduced Multiplicative Polynomial Kernel, a redefinition of the classical polynomial kernel equipped with a set of parameters that allows for a higher regularization. We tested the proposed approach in a simulated environment, and also in real experiments with a UR10 robot. The obtained results confirm that, compared to other data-driven estimators, the proposed approach is more data-efficient and exhibits better generalization properties. Instead, with respect to model-based estimators, our approach requires less prior information and is not affected by model bias.

关键词： Dynamics calibration and identification model learning for control

来源：评论

学校读者我要写书评

暂无评论

3D Path-Following Using MRAC on a Millimeter-Scale Spiral-Type Magnetic Robot

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 1564-1571页

作者： Zhao, Haoran Leclerc, Julien Feucht, Maria Bailey, Olivia Becker, Aaron T. Univ Houston Dept Elect & Comp Engn Houston TX 77004 USA Baylor Univ Waco TX 76706 USA Univ Maryland Baltimore Cty Baltimore MD 21250 USA

This letter focuses on the 3D path-following of a spiral-type helical magnetic swimmer in a water-filled workspace. The swimmer has a diameter of 2.5 mm, a length of 6 mm, and is controlled by an external time-varying magnetic field. A method to compensate undesired magnetic gradient forces is proposed and tested. Five swimmer designs with different thread pitch values were experimentally analyzed. All were controlled by the same model reference adaptive controller (MRAC). Compared to a conventional hand-tuned PI controller, their 3D path-following performance is significantly improved by using MRAC. At an average speed of ${\text{50}}\,\text{mm}$/s, the path-following mean error of the MRAC is 3.8$ \;\pm\;$1.8 mm, less than one body length of the swimmer. The versatility of this new controller is demonstrated by analyzing path-following through obstacles on a helical trajectory and forward & backward motion.

关键词： Medical robots and systems model learning for 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：