检索结果-内蒙古大学图书馆

2020 Conference on Artificial Life, ALIFE 2020

作者： Bartoli, Alberto Catto, Marco De Lorenzo, Andrea Medvet, Eric Talamini, Jacopo Machine Learning Lab. Department of Engineering and Architecture University of Trieste Italy Evolutionary Robotics and Artificial Life Lab. Department of Engineering and Architecture University of Trieste Italy

Adaptation of agents in artificial life scenarios is especially effective when agents may evolve, i.e., inherit traits from their parents, and learn by interacting with the environment. The learning process may be boosted with forms of social learning, i.e., by allowing an agent to learn by combining its experiences with knowledge transferred among agents. In this work, we tackle two specific questions regarding social learning and evolution: (a) from whom learners should learn? (b) how should knowledge be transferred? We address these questions by experimentally investigating two scenarios: a simple one in which the mechanism for evolution and learning is easily interpretable;a more complex and realistic artificial life scenario in which agents compete for survival. Experimental results show that social learning is more profitable when (a) the learners learn from a small set of good teachers and (b) the knowledge to be transferred is determined by teachers experience, rather than learner experience. © 2020 Massachusetts Institute of Technology.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Communication in Decision Making: Competition favors Inequality

Communication in Decision Making: Competition favors Inequal...

引用

2020 Conference on Artificial Life, ALIFE 2020

作者： Talamini, Jacopo Medvet, Eric Bartoli, Alberto De Lorenzo, Andrea Machine Learning Lab. Department of Engineering and Architecture University of Trieste Italy Evolutionary Robotics and Artificial Life Lab. Department of Engineering and Architecture University of Trieste Italy

We consider a multi-agent system in which the individual goal is to collect resources, but where the amount of collected resources depends also on others decision. Agents can communicate and can take advantage of being communicated other agents’ plan: therefore they may develop more profitable strategies. We wonder if some kind of collective behaviour, with respect to communication, emerges in this system without being explicitly promoted. To investigate this aspect, we design three different scenarios, respectively a cooperative, a competitive, and a mixed one, in which agents’ behaviors are individually learned by means of reinforcement learning. We consider different strategies concerning communication and learning, including no-communication, always-communication, and optional-communication. Experimental results show that always-communication leads to a collective behaviour with the best results in terms of both overall earned resources and equality between agents. On the other hand optional-communication strategy leads to similar collective strategies in some of these scenarios, but in other scenarios some agents develop individual behaviours that oppose to the collective welfare and thus result in high inequality. © 2020 Massachusetts Institute of Technology.

关键词：

来源：评论

学校读者我要写书评

暂无评论

POMDP manipulation via trajectory optimization

POMDP manipulation via trajectory optimization

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems

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

Efficient object manipulation based only on force feedback typically requires a plan of actively contact-seeking actions to reduce uncertainty over the true environmental model. In principle, that problem could be formulated as a full partially observable Markov decision process (POMDP) whose observations are sensed forces indicating the presence/absence of contacts with objects. Such a naive application leads to a very large POMDP with high-dimensional continuous state, action and observation spaces. Solving such large POMDPs is practically prohibitive. In other words, we are facing three challenging problems: 1) uncertainty over discontinuous contacts with objects;2) high-dimensional continuous spaces;3) optimization for not only trajectory cost but also execution time. As trajectory optimization is a powerful model-based method for motion generation, it can handle the last two issues effectively by computing locally optimal trajectories. This paper aims to integrate advantages of trajectory optimization into existing POMDP solvers. The full POMDP formulation is solved using sample-based approaches, where each sampled model is quickly evaluated via trajectory optimization instead of simulating a large number of rollouts. To further accelerate the solver, we propose to integrate temporal abstraction, i.e. macro actions or temporal actions, into the POMDP model. We demonstrate the proposed method on a simulated 7 DoF KUKA arm and a physical Willow Garage PR2 platform. The results show that our proposed method could effectively seek contacts in complex scenarios, and achieve near-optimal performance of path planing.

关键词： Trajectory optimization Robot sensing systems Uncertainty Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Classification of benign and malignant breast tumors in ultrasound images based on multiple sonographic and textural features

Classification of benign and malignant breast tumors in ultr...

引用

3rd International Conference on Intelligent Human-machine Systems and Cybernetics, IHMSC 2011

作者： Liao, Renjie Wan, Tao Qin, Zengchang Intelligent Computing and Machine Learning Lab. School of ASEE Beihang University Beijing 100191 China Robotics Institute Carnegie Mellon University United States

ISBN: (纸本)9780769544441

We establish a new set of features for differentiating benign from malignant breast lesions using ultrasound (US) images. Two types of features (sonographic and textural features) are considered. Among them, three sonographic features are novel. Sonograms of 321 pathologically proven breast cases are analyzed and classified into benign and malignant categories. The discrimination capability of the extracted features are evaluated using the support vector machines (SVM) in comparison with the results obtained from artificial neural networks (ANN) and K-nearest neighbor (KNN) classifier. The simulations demonstrate that the proposed algorithm can be an integral part to US computer-aided diagnosis (CAD) systems for breast cancer or an independent program to help accurately distinguish benign solid breast nodules from malignant nodules. © 2011 IEEE.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Kinematic morphing networks for manipulation skill transfer

arXiv

引用

arXiv 2018年

作者： Englert, Peter Toussaint, Marc Machine Learning & Robotics Lab University of Stuttgart Germany

The transfer of a robot skill between different geometric environments is non-trivial since a wide variety of environments exists, sensor observations as well as robot motions are high-dimensional, and the environment might only be partially observed. We consider the problem of extracting a low-dimensional description of the manipulated environment in form of a kinematic model. This allows us to transfer a skill by defining a policy on a prototype model and morphing the observed environment to this prototype. A deep neural network is used to map depth image observations of the environment to morphing parameter, which include transformation and configuration parameters of the prototype model. Using the concatenation property of affine transformations and the ability to convert point clouds to depth images allows to apply the network in an iterative manner. The network is trained on data generated in a simulator and on augmented data that is created by using network predictions. The algorithm is evaluated on different tasks, where it is shown that iterative predictions lead to a higher accuracy than one-step predictions. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of Human Full-Body Movements with Motion Optimization and Recurrent Neural Networks

Prediction of Human Full-Body Movements with Motion Optimiza...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Philipp Kratzer Marc Toussaint Jim Mainprice Machine Learning and Robotics Lab University of Stuttgart Germany

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

Human movement prediction is difficult as humans naturally exhibit complex behaviors that can change drastically from one environment to the next. In order to alleviate this issue, we propose a prediction framework that decouples short-term prediction, linked to internal body dynamics, and long-term prediction, linked to the environment and task constraints. In this work we investigate encoding short-term dynamics in a recurrent neural network, while we account for environmental constraints, such as obstacle avoidance, using gradient-based trajectory optimization. Experiments on real motion data demonstrate that our framework improves the prediction with respect to state-of-the-art motion prediction methods, as it accounts to beforehand unseen environmental structures. Moreover we demonstrate on an example, how this framework can be used to plan robot trajectories that are optimized to coordinate with a human partner.

关键词： Optimization Trajectory Predictive models Recurrent neural networks Collision avoidance Robot kinematics

来源：评论

学校读者我要写书评

暂无评论

Touch based POMDP manipulation via sequential submodular optimization

Touch based POMDP manipulation via sequential submodular opt...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Ngo Anh Vien Marc Toussaint Machine Learning & Robotics Lab University of Stuttgart Germany

Exploiting the submodularity of entropy-related objectives has recently led to a series of successes in machine learning and sequential decision making. Its generalized framework, adaptive submodularity, has later been introduced to deal with uncertainty and partially observability, achieving near-optimal performance with simple greedy policies. As a consequence, adaptive submodularity is in principle a promising candidate for efficient touch-based localization in robotics. However, applying that method directly on the motion level shows poor scaling with the dimensionality of the system. Being motivated by hierarchical partially observable Markov decision process (POMDP) planning, we integrate an action hierarchy into the existing adaptive submodularity framework. The proposed algorithm is expected to effectively generate uncertainty-reducing actions with the help from an action hierarchy. Experimental results on both, a simulated robot and a Willow Garage PR2 platform, demonstrate the efficiency of our algorithm.

关键词： Robot sensing systems Uncertainty Trajectory Optimization Planning Yttrium

来源：评论

学校读者我要写书评

暂无评论

Identification of unmodeled objects from symbolic descriptions

arXiv

引用

arXiv 2017年

作者： Baisero, Andrea Otte, Stefan Englert, Peter Toussaint, Marc Machine Learning and Robotics Lab University of Stuttgart Germany

Successful human-robot cooperation hinges on each agent's ability to process and exchange information about the shared environment and the task at hand. Human communication is primarily based on symbolic abstractions of object properties, rather than precise quantitative measures. A comprehensive robotic framework thus requires an integrated communication module which is able to establish a link and convert between perceptual and abstract information. The ability to interpret composite symbolic descriptions enables an autonomous agent to a) operate in unstructured and cluttered environments, in tasks which involve unmodeled or never seen before objects;and b) exploit the aggregation of multiple symbolic properties as an instance of ensemble learning, to improve identification performance even when the individual predicates encode generic information or are unprecisely grounded. We propose a discriminative probabilistic model which interprets symbolic descriptions to identify the referent object contextually w.r.t. the structure of the environment and other objects. The model is trained using a collected dataset of identifications, and its performance is evaluated by quantitative measures and a live demo developed on the PR2 robot platform, which integrates elements of perception, object extraction, object identification and grasping. Copyright © 2017, The Authors. All rights reserved.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Relational Activity Processes for Modeling Concurrent Cooperation

Relational Activity Processes for Modeling Concurrent Cooper...

引用

IEEE International Conference on robotics and Automation

作者： Marc Toussaint Thibaut Munzer Yoan Mollard Li Yang Wu Ngo Anh Vien Manuel Lopes Machine Learning and Robotics Lab University of Stuttgart Germany

ISBN: (纸本)9781467380270

In human-robot collaboration, multi-agent domains, or single-robot manipulation with multiple end-effectors, the activities of the involved parties are naturally concurrent. Such domains are also naturally relational as they involve objects, multiple agents, and models should generalize over objects and agents. We propose a novel formalization of relational concurrent activity processes that allows us to transfer methods from standard relational MDPs, such as Monte-Carlo planning and learning from demonstration, to concurrent cooperation domains. We formally compare the formulation to previous propositional models of concurrent decision making and demonstrate planning and learning from demonstration methods on a real-world human-robot assembly task.

关键词： Processes Modeling Concurrent

来源：评论

学校读者我要写书评

暂无评论

Regression with comparisons: escaping the curse of dimensionality with ordinal information

The Journal of Machine Learning Research

引用

The Journal of machine learning Research 2020年第1期21卷 6480-6533页

作者： Yichong Xu Sivaraman Balakrishnan Aarti Singh Artur Dubrawski Machine Learning Department Department of Statistics and Data Science Machine Learning Department Auton Lab The Robotics Institute Carnegie Mellon University Pittsburgh PA

In supervised learning, we typically leverage a fully labeled dataset to design methods for function estimation or prediction. In many practical situations, we are able to obtain alternative feedback, possibly at a low cost. A broad goal is to understand the usefulness of, and to design algorithms to exploit, this alternative feedback. In this paper, we consider a semi-supervised regression setting, where we obtain additional ordinal (or comparison) information for the unlabeled samples. We consider ordinal feedback of varying qualities where we have either a perfect ordering of the samples, a noisy ordering of the samples or noisy pairwise comparisons between the samples. We provide a precise quantification of the usefulness of these types of ordinal feedback in both nonparametric and linear regression, showing that in many cases it is possible to accurately estimate an underlying function with a very small labeled set, effectively escaping the curse of dimensionality. We also present lower bounds, that establish fundamental limits for the task and show that our algorithms are optimal in a variety of settings. Finally, we present extensive experiments on new datasets that demonstrate the efficacy and practicality of our algorithms and investigate their robustness to various sources of noise and model misspecification.

关键词： pairwise comparison ranking regression interactive learning

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：