检索结果-内蒙古大学图书馆

2017 IEEE International Conference on robotics and Automation, ICRA 2017

作者： Dries, Danny Englert, Peter Toussaint, Marc Machine Learning and Robotics Lab University of Stuttgart Germany

ISBN: (纸本)9781509046331

In this paper, we address the problem of how a robot can optimize parameters of combined interaction force/task space controllers under a success constraint in an active way. To enable the robot to explore its environment robustly, safely and without the risk of damaging anything, suitable control concepts have to be developed that enable compliant and force control in situations that are afflicted with high uncertainties. Instances of such concepts are impedance, operational space or hybrid control. However, the parameters of these controllers have to be tuned precisely in order to achieve reasonable performance, which is inherently challenging, as often no sufficient model of the environment is available. To overcome this, we propose to use constrained Bayesian optimization to enable the robot to tune its controller parameters autonomously. Unlike other controller tuning methods, this method allows us to include a success constraint into the optimization. Further, we introduce novel performance measures for compliant, force controlled robots. In real world experiments we show that our approach is able to optimize the parameters for a task that consists of establishing and maintaining contact between the robot and the environment efficiently and successfully. © 2017 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Efficient Over-parameterized Matrix Sensing from Noisy Measurements via Alternating Preconditioned Gradient Descent

arXiv

引用

arXiv 2025年

作者： Liu, Zhiyu Han, Zhi Tang, Yandong Zhang, Hai Tang, Shaojie Wang, Yao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Statistics Northwest University Xi’an710000 China Department of Management Science and Systems State University of New York Buffalo United States Center for Intelligent Decision-making and Machine Learning School of Management Xi’an Jiaotong University Xi’an710049 China

We consider the noisy matrix sensing problem in the over-parameterization setting, where the estimated rank r is larger than the true rank r★. Specifically, our main objective is to recover a matrix X★ ∈ Rn1×n2 with rank r★ from noisy measurements using an over-parameterized factorized form LRT, where L ∈ n1×r, R ∈ n2×r and min{n1, n2} ≥ r > r★, with the true rank r★ being unknown. Recently, preconditioning methods have been proposed to accelerate the convergence of matrix sensing problem compared to vanilla gradient descent, incorporating preconditioning terms (LTL + λI)−1 and (RTR + λI)−1 into the original gradient. However, these methods require careful tuning of the damping parameter λ and are sensitive to initial points and step size. To address these limitations, we propose the alternating preconditioned gradient descent (APGD) algorithm, which alternately updates the two factor matrices, eliminating the need for the damping parameter and enabling faster convergence with larger step sizes. We theoretically prove that APGD achieves near-optimal error convergence at a linear rate, starting from arbitrary random initializations. Through extensive experiments, we validate our theoretical results and demonstrate that APGD outperforms other methods, achieving the fastest convergence rate. Notably, both our theoretical analysis and experimental results illustrate that APGD does not rely on the initialization procedure, making it more practical and versatile. Copyright © 2025, The Authors. All rights reserved.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Model-based relational RL when object existence is partially observable 31

Model-based relational RL when object existence is partially...

引用

31st International Conference on machine learning, ICML 2014

作者： Vien, Ngo Anh Toussaint, Marc Machine Learning and Robotics Lab University of Stuttgart 70569 Germany

ISBN: (纸本)9781634393973

We consider learning and planning in relational MDPs when object existence is uncertain and new objects may appear or disappear depending on previous actions or properties of other ob-jects. Optimal policies actively need to discover objects to achieve a goal;planning in such domains in general amounts to a POMDP problem, where the belief is about the existence and properties of potential not-yet-discovered objects. We propose a computationally efficient extension of model-based relational RL methods that approximates these beliefs using discrete uncertainty predicates. In this formulation the belief update is learned using probabilistic rules and planning in the approximated belief space can be achieved using an extension of existing planners. We prove that the learned belief update rules encode an approximation of the exact belief updates of a POMDP formulation and demonstrate experimentally that the proposed approach successfully learns a set of relational rules appropriate to solve such problems. Copyright © (2014) by the International machine learning Society (IMLS) All rights reserved.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Monte-Carlo planning 29

Hierarchical Monte-Carlo planning

引用

29th AAAI Conference on Artificial Intelligence, AAAI 2015 and the 27th Innovative Applications of Artificial Intelligence Conference, IAAI 2015

作者： Vien, Ngo Anh Toussaint, Marc Machine Learning and Robotics Lab. University of Stuttgart Germany

ISBN: (纸本)9781577357032

Monte-Carlo Tree Search, especially UCT and its POMDP version POMCP, have demonstrated excellent performance on many problems. However, to efficiently scale to large domains one should also exploit hierarchical structure if present. In such hierarchical domains, finding rewarded states typically requires to search deeply;covering enough such informative states very far from the root becomes computationally expensive in fiat non-hierarchical search approaches. We propose novel, scalable MCTS methods which integrate a task hierarchy into the MCTS framework, specifically leading to hierarchical versions of both, UCT and POMCP. The new method does not need to estimate probabilistic models of each subtask, it instead computes subtask policies purely sample-based. We evaluate the hierarchical MCTS methods on various settings such as a hierarchical MDP, a Bayesian model-based hierarchical RL problem, and a large hierarchical POMDP. © Copyright 2015, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

When explanations lie: Why many modified BP attributions fail 37

When explanations lie: Why many modified BP attributions fai...

引用

37th International Conference on machine learning, ICML 2020

作者： Sixt, Leon Granz, Maximilian Landgraf, Tim Dahlem Center of Machine Learning and Robotics Freie Universität Berlin Germany

ISBN: (纸本)9781713821120

Attribution methods aim to explain a neural network's prediction by highlighting the most relevant image areas. A popular approach is to backpropagate (BP) a custom relevance score using modified rules, rather than the gradient. We analyze an extensive set of modified BP methods: Deep Taylor Decomposition, Layer-wise Relevance Propagation (LRP), Excitation BP, PatternAttribution, DeepLIFT, Deconv, RectGrad, and Guided BP. We find empirically that the explanations of all mentioned methods, except for DeepLIFT, are independent of the parameters of later layers. We provide theoretical insights for this surprising behavior and also analyze why DeepLIFT does not suffer from this limitation. Empirically, we measure how information of later layers is ignored by using our new metric, cosine similarity convergence (CSC). The paper provides a framework to assess the faithfulness of new and existing modified BP methods theoretically and empirically. © 2020 37th International Conference on machine learning, ICML 2020. All rights reserved.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Automated Multilingual Detection of Pro-Kremlin Propaganda in Newspapers and Telegram Posts

引用

Datenbank-Spektrum 2023年第1期23卷 5-14页

作者： Solopova, Veronika Popescu, Oana-Iuliana Benzmüller, Christoph Landgraf, Tim Dahlem Center for Machine Learning and Robotics Freie Universität Berlin Berlin Germany German Aerospace Center Jena Germany

The full-scale conflict between the Russian Federation and Ukraine generated an unprecedented amount of news articles and social media data reflecting opposing ideologies and narratives. These polarized campaigns have led to mutual accusations of misinformation and fake news, shaping an atmosphere of confusion and mistrust for readers worldwide. This study analyses how the media affected and mirrored public opinion during the first month of the war using news articles and Telegram news channels in Ukrainian, Russian, Romanian, French and English. We propose and compare two methods of multilingual automated pro-Kremlin propaganda identification, based on Transformers and linguistic features. We analyse the advantages and disadvantages of both methods, their adaptability to new genres and languages, and ethical considerations of their usage for content moderation. With this work, we aim to lay the foundation for further development of moderation tools tailored to the current conflict. © 2023, The Author(s).

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Subspace Clustering

引用

IEEE SIGNAL PROCESSING MAGAZINE 2011年第2期28卷 52-68页

作者： Vidal, Rene He was coeditor of the book Dynamical Vision and has coauthored more than 100 articles in biomedical image analysis computer vision machine learning hybrid systems and robotics.

The past few years have witnessed an explosion in the availability of data from multiple sources and modalities. For example, millions of cameras have been installed in buildings, streets, airports, and cities around the world. This has generated extraordinary advances on how to acquire, compress, store, transmit, and process massive amounts of complex high-dimensional data.

关键词： Principal component analysis Polynomials Clustering algorithms Signal processing algorithms Noise Data models Subspace constraints

来源：评论

学校读者我要写书评

暂无评论

Task space retrieval using inverse feedback control

Task space retrieval using inverse feedback control

引用

28th International Conference on machine learning, ICML 2011

作者： Jetchev, Nikolay Toussaint, Marc Machine Learning and Robotics Lab. FU Berlin Arnimallee 7 14195 Berlin Germany

ISBN: (纸本)9781450306195

learning complex skills by repeating and generalizing expert behavior is a fundamental problem in robotics. A common approach is learning from demonstration: given examples of correct motions, learn a policy mapping state to action consistent with the training data. However, the usual approaches do not answer the question of what are appropriate representations to generate motions for specific tasks. Inspired by Inverse Optimal Control, we present a novel method to learn latent costs, imitate and generalize demonstrated behavior, and discover a task relevant motion representation: Task Space Retrieval Using Inverse Feedback Control (TRIC). We use the learned latent costs to create motion with a feedback controller. We tested our method on robot grasping of objects, a challenging high-dimensional task. TRIC learns the important control dimensions for the grasping task from a few example movements and is able to robustly approach and grasp objects in new situations. Copyright 2011 by the author(s)/owner(s).

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

Autonomous Car Navigation Using Vector Fields

Autonomous Car Navigation Using Vector Fields

引用

2018 IEEE Intelligent Vehicles Symposium, IV 2018

作者： Boroujeni, Zahra Mohammadi, Mostafa Neumann, Daniel Goehring, Daniel Rojas, Raul Dahlem Center for Machine Learning and Robotics Computer Science Institute Freie Universität Berlin Germany

ISBN: (纸本)9781538644522

In this paper, a method based on vector fields for the navigation of autonomous cars is developed. Vector fields-used to generate the desired heading angle of a vehicle toward a specified road lane - attract the car to the desired path and prevent the car from colliding with obstacles. Also, a control law is developed to define the velocity direction and the desired steering angle based on the angle between the car and the vector field. The efficacy of the proposed approach is investigated through several simulations and lab experimental tests. © 2018 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Probabilistic backward and forward reasoning in stochastic relational worlds

Probabilistic backward and forward reasoning in stochastic r...

引用

27th International Conference on machine learning, ICML 2010

作者： Lang, Tobias Toussaint, Marc Machine Learning and Robotics Group TU Berlin Franklinstraße 28/29 10587 Berlin Germany

ISBN: (纸本)9781605589077

Inference in graphical models has emerged as a promising technique for planning. A recent approach to decision-theoretic planning in relational domains uses forward inference in dynamic Bayesian networks compiled from learned probabilistic relational rules. Inspired by work in non-relational domains with small state spaces, we derive a back-propagation method for such nets in relational domains starting from a goal state mixture distribution. We combine this with forward reasoning in a bidirectional two-filter approach. We perform experiments in a complex 3D simulated desktop environment with an articulated manipulator and realistic physics. Empirical results show that bidirectional probabilistic reasoning can lead to more efficient and accurate planning in comparison to pure forward reasoning. Copyright 2010 by the author(s)/owner(s).

关键词： Backpropagation

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：