检索结果-内蒙古大学图书馆

Discovering Interpretable Dynamics by Sparsity Promotion on Energy and the Lagrangian

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 2154-2160页

作者： Chu, Hoang K. Hayashibe, Mitsuhiro Tohoku Univ Grad Sch Engn Dept Robot Neurorobot Lab Sendai Miyagi 9808579 Japan

Data-driven modeling frameworks that adopt sparse regression techniques, such as sparse identification of nonlinear dynamics (SINDy) and its modifications, are developed to resolve difficulties in extracting underlying dynamics from experimental data. In contrast to neural-network-based methods, these methods are designed to obtain white-box analytical models. In this work, we incorporate the concept of SINDy and knowledge in the field of classical mechanics to identify interpretable and sparse expressions of total energy and the Lagrangian that shelters the hidden dynamics. Moreover, our method (hereafter referred as Lagrangian-SINDy) is developed to use knowledge of simple systems that form the system being analyzed to ensure the likelihood of correct results and to improve the learning pace. Lagrangian-SINDy is highly accurate in discovering interpretable dynamics via energy-related physical quantities. Its performance is validated with three popular multi-DOF nonlinear dynamical systems, namely the spherical pendulum, double pendulum and cart-pendulum system. Comparisons with other SINDy-based methods are made and Lagrangian-SINDy is found to provide the most compact analytical models.

关键词： Dynamics calibration and identification dynamics model learning for control

来源：评论

学校读者我要写书评

暂无评论

model-Based Reinforcement learning for Physical Systems Without Velocity and Acceleration Measurements

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 3548-3555页

作者： Dalla Libera, Alberto Romeres, Diego Jha, Devesh K. Yerazunis, Bill Nikovski, Daniel Univ Padua Dept Informat Engn I-35131 Padua Italy Mitsubishi Elect Res Labs Cambridge MA 02139 USA

In this letter, we propose a derivative-free model learning framework for Reinforcement learning (RL) algorithms based on Gaussian Process Regression (GPR). In many mechanical systems, only positions can be measured by the sensing instruments. Then, instead of representing the system state as suggested by the physics with a collection of positions, velocities, and accelerations, we define the state as the set of past position measurements. However, the equation of motions derived by physical first principles cannot be directly applied in this framework, being functions of velocities and accelerations. For this reason, we introduce a novel derivative-free physically-inspired kernel, which can be easily combined with nonparametric derivative-free Gaussian Process models. Tests performed on two real platforms show that the considered state definition combined with the proposed model improves estimation performance and data-efficiency w.r.t. traditional models based on GPR. Finally, we validate the proposed framework by solving two RL control problems for two real robotic systems.

关键词： Ground penetrating radar Kernel Acceleration Mathematical model Computational modeling Heuristic algorithms Standards model learning for control dynamics reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Heteroscedastic Uncertainty for Robust Generative Latent Dynamics

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第4期5卷 6654-6661页

作者： Limoyo, Oliver Chan, Bryan Maric, Filip Wagstaff, Brandon Mahmood, A. Rupam Kelly, Jonathan Univ Toronto Space & Terr Autonomous Robot Syst STARS Lab Inst Aerosp Studies UTIAS Toronto ON M3H 5T6 Canada Univ Zagreb Lab Autonomous Syst & Mobile Robot LAMOR Zagreb 10000 Croatia Univ Alberta Reinforcement Learning & Artificial Intelligence Edmonton AB T6G 2R3 Canada

learning or identifying dynamics from a sequence of high-dimensional observations is a difficult challenge in many domains, including reinforcement learning, and control. The problem has recently been studied from a generative perspective through latent dynamics: high-dimensional observations are embedded into a lower-dimensional space in which the dynamics can be learned. Despite some successes, latent dynamics models have not yet been applied to real-world robotic systems where learned representations must be robust to a variety of perceptual confounds, and noise sources not seen during training. In this letter, we present a method to jointly learn a latent state representation, and the associated dynamics that is amenable for long-term planning, and closed-loop control under perceptually difficult conditions. As our main contribution, we describe how our representation is able to capture a notion of heteroscedastic or input-specific uncertainty at test time by detecting novel or out-of-distribution (OOD) inputs. We present results from prediction, and control experiments on two image-based tasks: a simulated pendulum balancing task, and a real-world robotic manipulator reaching task. We demonstrate that our model produces significantly more accurate predictions, and exhibits improved control performance, compared to a model that assumes homoscedastic uncertainty only, in the presence of varying degrees of input degradation.

关键词： model learning for control visual learning reinforcement learning calibration and identification

来源：评论

学校读者我要写书评

暂无评论

Investigation of a Hybrid Kinematic Calibration Method for the "Sina" Surgical Robot

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第4期5卷 5276-5282页

作者： Alamdar, Alireza Samandi, Pouya Hanifeh, Shahrzad Kheradmand, Pejman Mirbagheri, Alireza Farahmand, Farzam Sarkar, Saeed Univ Tehran Med Sci Res Ctr Biomed Technol & Robot RCBTR Adv Med Technol & Equipment Inst AMTEI Tehran *** Iran Johns Hopkins Univ Lab Computat Sensing & Robot Baltimore MD 21218 USA Univ Tehran Med Sci Med Phys & Biomed Engn Dept Sch Med Tehran *** Iran Sharif Univ Technol Dept Mech Engn Tehran *** Iran

Calibrating the inverse kinematics of complex robots is often a challenging task. Finding analytical solutions is not always possible and the convergence of numerical methods is not guaranteed. The model-free approaches, based on machine learning and artificial intelligence, are fast and easy to work, however, they need a huge amount of experimental training data to provide acceptable results. In this article, we proposed a hybrid method to benefit the advantage of both model-based and model-free approaches. The forward kinematics of the robot is calibrated using a model-based approach, and its inverse kinematics using a neural network. Hence, while there is no need to solve the nonlinear inverse kinematic equations, the training data of the neural network is generated artificially by the calibrated forward kinematic model. The implementation of the proposed methodology on slave robot of the "Sina" surgical system revealed reasonably good results. The accuracy improved by 53% and 43% for position and orientation, respectively, after calibration.

关键词： Medical robots and systems kinematics calibration and identification model learning for control artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Benchmark for Bimanual Robotic Manipulation of Semi-Deformable Objects

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 2443-2450页

作者： Chatzilygeroudis, Konstantinos Fichera, Bernardo Lauzana, Ilaria Bu, Fanjun Yao, Kunpeng Khadivar, Farshad Billard, Aude Ecole Polytech Fed Lausanne Learning Algorithms & Syst Lab CH-1015 Lausanne Switzerland Johns Hopkins Univ Baltimore MD 21218 USA

We propose a new benchmarking protocol to evaluate algorithms for bimanual robotic manipulation semi-deformable objects. The benchmark is inspired from two real-world applications: (a) watchmaking craftsmanship, and (b) belt assembly in automobile engines. We provide two setups that try to highlight the following challenges: (a) manipulating objects via a tool, (b) placing irregularly shaped objects in the correct groove, (c) handling semi-deformable objects, and (d) bimanual coordination. We provide CAD drawings of the task pieces that can be easily 3D printed to ensure ease of reproduction, and detailed description of tasks and protocol for successful reproduction, as well as meaningful metrics for comparison. We propose four categories of submission in an attempt to make the benchmark accessible to a wide range of related fields spanning from adaptive control, motion planning to learning the tasks through trial-and-error learning.

关键词： Performance evaluation and benchmarking dual arm manipulation model learning for control dexterous manipulation

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Approach to Prediction and Optimal Bucket-Filling control for Autonomous Excavators

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 2682-2689页

作者： Sandzimier, Ryan J. Asada, H. Harry MIT Dept Mech Engn Cambridge MA 02139 USA

We develop a data-driven, statistical control method for autonomous excavators. Interactions between soil and an excavator bucket are highly complex and nonlinear, making traditional physical modeling difficult to use for real-time control. Here, we propose a data-driven method, exploiting data obtained from laboratory tests. We use the data to construct a nonlinear, non-parametric statistical model for predicting the behavior of soil scooped by an excavator bucket. The prediction model is built for controlling the amount of soil collected with a bucket. An excavator collects soil by dragging the bucket along the soil surface and scooping the soil by rotating the bucket. It is important to switch from the drag phase to the scoop phase with the correct timing to ensure an appropriate amount of soil has accumulated in front of the bucket. We model the process as a heteroscedastic Gaussian process (GP) based on the observation that the variance of the collected soil mass depends on the scooping trajectory, i.e., the input, as well as the shape of the soil surface immediately prior to scooping. We develop an optimal control algorithm for switching from the drag phase to the scoop phase at an appropriate time and for generating a scoop trajectory to capture a desired amount of soil with high confidence. We implement the method on a robotic excavator and collect experimental data. Experiments show promising results in terms of being able to achieve a desired bucket fill factor with low variance.

关键词： Data-driven control Gaussian process robotics in construction mining robotics field robots model learning for control optimization and optimal control probability and statistical methods

来源：评论

学校读者我要写书评

暂无评论

model-Based Generalization Under Parameter Uncertainty Using Path Integral control

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 2864-2871页

作者： Abraham, Ian Handa, Ankur Ratliff, Nathan Lowrey, Kendall Murphey, Todd D. Fox, Dieter NVIDIA Santa Clara CA 95050 USA Northwestern Univ Evanston IL 60208 USA Univ Washington Seattle WA 98105 USA Northwestern Univ Evanston IL 60208 USA

This letter addresses the problem of robot interaction in complex environments where online control and adaptation is necessary. By expanding the sample space in the free energy formulation of path integral control, we derive a natural extension to the path integral control that embeds uncertainty into action and provides robustness for model-based robot planning. Our algorithm is applied to a diverse set of tasks using different robots and validate our results in simulation and real-world experiments. We further show that our method is capable of running in real-time without loss of performance. Videos of the experiments as well as additional implementation details can be found at https://***/view/emppi.

关键词： model learning for control learning and adaptive systems

来源：评论

学校读者我要写书评

暂无评论

Real-Time Nonlinear model Predictive control of Robots Using a Graphics Processing Unit

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第2期5卷 1468-1475页

作者： Hyatt, Phillip Killpack, Marc D. Brigham Young Univ Mech Engn Dept Provo UT 84602 USA

In past robotics applications, model Predictive control (MPC) has often been limited to linear models and relatively short time horizons. In recent years however, research in optimization, optimal control, and simulation has enabled some forms of nonlinear model predictive control which find locally optimal solutions. The limiting factor for applying nonlinear MPC for robotics remains the computation necessary to solve the optimization, especially for complex systems and for long time horizons. This letter presents a new solution method which addresses computational concerns related to nonlinear MPC called nonlinear Evolutionary MPC (NEMPC), and then we compare it to several existing methods. These comparisons include simulations on torque-limited robots performing a swing-up task and demonstrate that NEMPC is able to discover complex behaviors to accomplish the task. Comparisons with state-of-the-art nonlinear MPC algorithms show that NEMPC finds high quality control solutions very quickly using a global, instead of local, optimization method. Finally, an application in hardware (a 24 state pneumatically actuated continuum soft robot) demonstrates that this method is tractable for real-time control of high degree of freedom systems.

关键词： Optimization and optimal control control architectures and programming deep learning in robotics and automation model learning for control

来源：评论

学校读者我要写书评

暂无评论

Efficiently Calibrating Cable-Driven Surgical Robots With RGBD Fiducial Sensing and Recurrent Neural Networks

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第4期5卷 5937-5944页

作者： Hwang, Minho Thananjeyan, Brijen Paradis, Samuel Seita, Daniel Ichnowski, Jeffrey Fer, Danyal Low, Thomas Goldberg, Ken Univ Calif Berkeley Berkeley CA 94708 USA UCSF East Bay Oakland CA 94602 USA SRI Int 333 Ravenswood Ave Menlo Pk CA 94025 USA

Automation of surgical subtasks using cable-driven robotic surgical assistants (RSAs) such as Intuitive Surgical's da Vinci Research Kit (dVRK) is challenging due to imprecision in control from cable-related effects such as cable stretching and hysteresis. We propose a novel approach to efficiently calibrate such robots by placing a 3D printed fiducial coordinate frames on the arm and end-effector that is tracked using RGBD sensing. To measure the coupling and history-dependent effects between joints, we analyze data from sampled trajectories and consider 13 approaches to modeling. These models include linear regression and LSTM recurrent neural networks, each with varying temporal window length to provide compensatory feedback. With the proposed method, data collection of 1800 samples takes 31 minutes and model training takes under 1 minute. Results on a test set of reference trajectories suggest that the trained model can reduce the mean tracking error of physical robot from 2.96 mm to 0.65 mm. Results on the execution of open-loop trajectories of the FLS peg transfer surgeon training task suggest that the best model increases success rate from 39.4% to 96.7%, producing performance comparable to that of an expert surgical resident. Supplementary materials, including code and 3D-printable models, are available at https://***/***/surgical-calibration.

关键词： Calibration and identification model learning for control medical robots and systems

来源：评论

学校读者我要写书评

暂无评论

Cooperative Comfortable-Driving at Signalized Intersections for Connected and Automated Vehicles

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2020年第4期5卷 6247-6254页

作者： Shen, Xun Zhang, Xingguo Ouyang, Tinghui Li, Yuanchao Raksincharoensak, Pongsathorn Tokyo Univ Agr & Technol Dept Mech Syst Engn Koganei Tokyo 1848588 Japan Natl Inst Adv Ind Sci & Technol Artificial Intelligence Res Ctr Tokyo Bay Area Ctr Tokyo 1350064 Japan Honda Res & Dev Co Ltd Honda Innovat Lab Tokyo Tokyo 1076238 Japan

This letter proposes a control framework for Connected and Automated Vehicles(CAVs) to approach the signalized intersections with good driving-comfortability. Both the velocity plan and longitudinal dynamics control are concerned in this study. Regarding the velocity plan problem, a two-layer framework is designed. First, a scenario identifier method is proposed to identify which scenario the target velocity profile should be according to the current vehicle speed, distance to the intersection, and traffic signal information. Then, an assigned-time velocity planning problem with velocity and acceleration constraints is formulated and solved to obtain a smooth velocity profile with the minimal jerk. For the longitudinal dynamics control, a predictive controller with Online Sequential Extreme learning Machine(OSELM) is applied to realize the smooth velocity profile tracking. CarMaker-Simulink co-simulation has been conducted to validate the proposed method. The validation results show that the proposed method can identify the scenario in 100% of the time according to the validation results. On the other hand, the OSELM-based predictive control has improved MSE e(v), e(a), e(jerk) of 33.85%, 27.66%, and 38.03% respectively than PID control.

关键词： Intelligent transportation systems motion and path planning 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：