检索结果-内蒙古大学图书馆

36th International Conference on Machine learning, ICML 2019

作者： Becker, Philipp Pandya, Harit Gebhardt, Gregor Zhao, Cheng Taylor, James Neumann, Gerhard Computational Learning for Autonomous Systems TU Darmstadt Darmstadt Germany Bosch Center for Artificial Intelligence Renningen Germany University of Tübingen Tübingen Germany Lincoln Center for Autonomous Systems University of Lincoln Lincoln United Kingdom Extreme Robotics Lab University of Birmingham Birmingham United Kingdom Engineering Department Lancaster University Lancaster United Kingdom

ISBN: (纸本)9781510886988

In order to integrate uncertainty estimates into deep time-series modelling, Kaiman Filters (KFs) (Kaiman et al., 1960) have been integrated with deep learning models, however, such approaches typically rely on approximate inference techniques such as variational inference which makes learning more complex and often less scalable due to approximation errors. We propose a new deep approach to Kaiman filtering which can be learned directly in an end-to-end manner using backpropagation without additional approximations. Our approach uses a high-dimensional factorized latent state representation for which the Kaiman updates simplify to scalar operations and thus avoids hard to backpropagate, computationally heavy and potentially unstable matrix inversions. Moreover, we use locally linear dynamic models to efficiently propagate the latent state to the next time step. The resulting network architecture, which we call Recurrent Kaiman Network (RKN), can be used for any time-series data, similar to a LSTM (Hochreiter & Schmidhuber, 1997) but uses an explicit representation of uncertainty. As shown by our experiments, the RKN obtains much more accurate uncertainty estimates than an LSTM or Gated Recurrent Units (GRUs) (Cho et al., 2014) while also showing a slightly improved prediction performance and outperforms various recent generative models on an image imputation task. © 36th International Conference on Machine learning, ICML 2019. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Recurrent kalman networks: Factorized inference in high-dimensional deep feature spaces

arXiv

引用

arXiv 2019年

In order to integrate uncertainty estimates into deep time-series modelling, Kalman Filters (KFs) (Kalman et al., 1960) have been integrated with deep learning models, however, such approaches typically rely on approximate inference techniques such as variational inference which makes learning more complex and often less scalable due to approximation errors. We propose a new deep approach to Kalman filtering which can be learned directly in an end-to-end manner using backpropagation without additional approximations. Our approach uses a high-dimensional factorized latent state representation for which the Kalman updates simplify to scalar operations and thus avoids hard to backpropagate, computationally heavy and potentially unstable matrix inversions. Moreover, we use locally linear dynamic models to efficiently propagate the latent state to the next time step. The resulting network architecture, which we call Recurrent Kalman Network (RKN), can be used for any time-series data, similar to a LSTM (Hochreiter & Schmidhuber, 1997) but uses an explicit representation of uncertainty. As shown by our experiments, the RKN obtains much more accurate uncertainty estimates than an LSTM or Gated Recurrent Units (GRUs) (Cho et al., 2014) while also showing a slightly improved prediction performance and outperforms various recent generative models on an image imputation task. Copyright © 2019, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Model-based policy search for automatic tuning of multivariate PID controllers

Model-based policy search for automatic tuning of multivaria...

引用

2017 IEEE International Conference on Robotics and Automation, ICRA 2017

作者： Doerr, Andreas Nguyen-Tuong, Duy Marco, Alonso Schaal, Stefan Trimpe, Sebastian Bosch Center for Artificial Intelligence Renningen Germany Autonomous Motion Department Max Planck Institute for Intelligent Systems Tübingen Germany Computational Learning and Motor Control Lab University of Southern California Los AngelesCA United States

ISBN: (纸本)9781509046331

PID control architectures are widely used in industrial applications. Despite their low number of open parameters, tuning multiple, coupled PID controllers can become tedious in practice. In this paper, we extend PILCO, a model-based policy search framework, to automatically tune multivariate PID controllers purely based on data observed on an otherwise unknown system. The system's state is extended appropriately to frame the PID policy as a static state feedback policy. This renders PID tuning possible as the solution of a finite horizon optimal control problem without further a priori knowledge. The framework is applied to the task of balancing an inverted pendulum on a seven degree-of-freedom robotic arm, thereby demonstrating its capabilities of fast and data-efficient policy learning, even on complex real world problems. © 2017 IEEE.

关键词： Inverted pendulum

来源：评论

学校读者我要写书评

暂无评论

Balancing and walking using full dynamics LQR control with contact constraints

arXiv

引用

arXiv 2017年

作者： Mason, Sean Rotella, Nicholas Schaal, Stefan Righetti, Ludovic Computational Learning and Motor Control Lab University of Southern California Los AngelesCA United States Autonomous Motion Department Max Planck Institute for Intelligent Systems Tuebingen Germany

Torque control algorithms which consider robot dynamics and contact constraints are important for creating dynamic behaviors for humanoids. As computational power increases, algorithms tend to also increase in complexity. However, it is not clear how much complexity is really required to create controllers which exhibit good performance. In this paper, we study the capabilities of a simple approach based on contact consistent LQR controllers designed around key poses to control various tasks on a humanoid robot. We present extensive experimental results on a hydraulic, torque controlled humanoid performing balancing and stepping tasks. This feedback control approach captures the necessary synergies between the DoFs of the robot to guarantee good control performance. We show that for the considered tasks, it is only necessary to re-linearize the dynamics of the robot at different contact configurations and that increasing the number of LQR controllers along desired trajectories does not improve performance. Our result suggest that very simple controllers can yield good performance competitive with current state of the art, but more complex, optimization-based whole-body controllers. A video of the experiments can be found at https://***/5T08CNKV1hw. Copyright © 2017, The Authors. All rights reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Combining learned and analytical models for predicting action effects from sensory data

arXiv

引用

arXiv 2017年

作者： Kloss, Alina Schaal, Stefan Bohg, Jeannette Autonomous Motion Department Max Planck Institute for Intelligent Systems Germany Computational Learning and Motor Control Lab University of Southern California United States Department of Computer Science Stanford University United States

One of the most basic skills a robot should possess is predicting the effect of physical interactions with objects in the environment. This enables optimal action selection to reach a certain goal state. Traditionally, dynamics are approximated by physics-based analytical models. These models rely on specific state representations that may be hard to obtain from raw sensory data, especially if no knowledge of the object shape is assumed. More recently, we have seen learning approaches that can predict the effect of complex physical interactions directly from sensory input. It is however an open question how far these models generalize beyond their training data. In this work, we investigate the advantages and limitations of neural network based learning approaches for predicting the effects of actions based on sensory input and show how analytical and learned models can be combined to leverage the best of both worlds. As physical interaction task, we use planar pushing, for which there exists a well-known analytical model and a large realworld dataset. We propose to use a convolutional neural network to convert raw depth images or organized point clouds into a suitable representation for the analytical model and compare this approach to using neural networks for both, perception and prediction. A systematic evaluation of the proposed approach on a very large real-world dataset shows two main advantages of the hybrid architecture. Compared to a pure neural network, it significantly (i) reduces required training data and (ii) improves generalization to novel physical interaction. Copyright © 2017, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Model-based policy search for automatic tuning of multivariate PID controllers

Model-based policy search for automatic tuning of multivaria...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Andreas Doerr Duy Nguyen-Tuong Alonso Marco Stefan Schaal Sebastian Trimpe Autonomous Motion Department at the Max Planck Institute for Intelligent Systems Tübingen Germany Bosch Center for Artificial Intelligence Renningen Germany Computational Learning and Motor Control lab at the University of Southern California Los Angeles CA USA

关键词： Tuning PD control PI control computational modeling Data models State feedback Process control

来源：评论

学校读者我要写书评

暂无评论

Model-based policy search for automatic tuning of multivariate pid controllers

arXiv

引用

arXiv 2017年

作者： Doerr, Andreas Nguyen-Tuong, Duy Marco, Alonso Schaal, Stefan Trimpe, Sebastian Bosch Center for Artificial Intelligence Renningen Germany Autonomous Motion Department Max Planck Institute for Intelligent Systems Tübingen Germany Computational Learning and Motor Control lab University of Southern California Los AngelesCA United States

关键词： Proportional control systems

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Contact learning for Humanoid Estimation and Control

arXiv

引用

arXiv 2017年

作者： Rotella, Nicholas Schaal, Stefan Righetti, Ludovic Computational Learning and Motor Control Lab University of Southern California Los AngelesCA United States Autonomous Motion Department Max Planck Institute for Intelligent Systems Tuebingen Germany New York University New YorkNY United States

This work presents a method for contact state estimation using fuzzy clustering to learn contact probability for full, six-dimensional humanoid contacts. The data required for training is solely from proprioceptive sensors - endeffector contact wrench sensors and inertial measurement units (IMUs) - and the method is completely unsupervised. The resulting cluster means are used to efficiently compute the probability of contact in each of the six endeffector degrees of freedom (DoFs) independently. This clustering-based contact probability estimator is validated in a kinematics-based base state estimator in a simulation environment with realistic added sensor noise for locomotion over rough, low-friction terrain on which the robot is subject to foot slip and rotation. The proposed base state estimator which utilizes these six DoF contact probability estimates is shown to perform considerably better than that which determines kinematic contact constraints purely based on measured normal force. Copyright © 2017, The Authors. All rights reserved.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

An MPC walking framework with external contact forces

arXiv

引用

arXiv 2017年

作者： Mason, Sean Rotella, Nicholas Schaal, Stefan Righetti, Ludovic Computational Learning and Motor Control Lab. University of Southern California Los AngelesCA United States Autonomous Motion Department Max Planck Institute for Intelligent Systems Tuebingen Germany Tandon School of Engineering New York University New York United States

In this work, we present an extension to a linear Model Predictive Control (MPC) scheme that plans external contact forces for the robot when given multiple contact locations and their corresponding friction cone. To this end, we set up a two-step optimization problem. In the first optimization, we compute the Center of Mass (CoM) trajectory, foot step locations, and introduce slack variables to account for violating the imposed constraints on the Zero Moment Point (ZMP). We then use the slack variables to trigger the second optimization, in which we calculate the optimal external force that compensates for the ZMP tracking error. This optimization considers multiple contacts positions within the environment by formulating the problem as a Mixed Integer Quadratic Program (MIQP) that can be solved at a speed between 100-300 Hz. Once contact is created, the MIQP reduces to a single Quadratic Program (QP) that can be solved in real-time ( Copyright © 2017, The Authors. All rights reserved.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Optimal control and inverse optimal control by distribution matching

Optimal control and inverse optimal control by distribution ...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems

作者： Oleg Arenz Hany Abdulsamad Gerhard Neumann Computational Learning for Autonomous Systems TU Darmstadt 64287 Germany Intelligent Autonomous Systems TU Darmstadt 64287 Germany

ISBN: (纸本)9781509037636

Optimal control is a powerful approach to achieve optimal behavior. However, it typically requires a manual specification of a cost function which often contains several objectives, such as reaching goal positions at different time steps or energy efficiency. Manually trading-off these objectives is often difficult and requires a high engineering effort. In this paper, we present a new approach to specify optimal behavior. We directly specify the desired behavior by a distribution over future states or features of the states. For example, the experimenter could choose to reach certain mean positions with given accuracy/variance at specified time steps. Our approach also unifies optimal control and inverse optimal control in one framework. Given a desired state distribution, we estimate a cost function such that the optimal controller matches the desired distribution. If the desired distribution is estimated from expert demonstrations, our approach performs inverse optimal control. We evaluate our approach on several optimal and inverse optimal control tasks on non-linear systems using incremental linearizations similar to differential dynamic programming approaches.

关键词： Optimal control Entropy Heuristic algorithms Trajectory Cost function learning (artificial intelligence)

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：