检索结果-内蒙古大学图书馆

28th International Conference on Automation and Computing, ICAC 2023

作者： Dai, Zhuangzhuang Park, Jinha Kaszowska, Aleksandra Li, Chen School of Engineering and Applied Science Aston University Dept. of Computer Science Engineering and Physical Science BirminghamB4 7ET United Kingdom The Maersk Mc Kinney Moller Institute University of Southern Denmark Sdu Robotics Odense5230 Denmark Aalborg University Department of Electronic Systems Aalborg9220 Denmark Aalborg University The Department of Materials and Production Aalborg9220 Denmark

ISBN: (纸本)9798350335859

The advent of industrial robotics and autonomous systems endow human-robot collaboration in a massive scale. However, current industrial robots are restrained in co-working with human in close proximity due to inability of interpreting human agents' attention. Human attention study is non-trivial since it involves multiple aspects of the mind: perception, memory, problem solving, and consciousness. Human attention lapses are particularly problematic and potentially catastrophic in industrial workplace, from assembling electronics to oper-ating machines. Attention is indeed complex and cannot be easily measured with single-modality sensors. Eye state, head pose, posture, and manifold environment stimulus could all play a part in attention lapses. To this end, we propose a pipeline to annotate multimodal dataset of human attention tracking, including eye tracking, fixation detection, third-person surveil-lance camera, and sound. We produce a pilot dataset containing two fully annotated phone assembly sequences in a realistic manufacturing environment. We evaluate existing fatigue and drowsiness prediction methods for attention lapse detection. Experimental results show that human attention lapses in production scenarios are more subtle and imperceptible than well-studied fatigue and drowsiness. © 2023 IEEE.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Causal normalizing flows: from theory to practice 23

Causal normalizing flows: from theory to practice

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Adrián Javaloy Pablo Sánchez-Martín Isabel Valera Department of Computer Science of Saarland University Saarbrücken Germany Department of Computer Science of Saarland University Saarbrücken Germany and Max Planck Institute for Intelligent Systems Tübingen Germany Department of Computer Science of Saarland University Saarbrücken Germany and Max Planck Institute for Software Systems Saarbrücken Germany

In this work, we deepen on the use of normalizing flows for causal inference. Specifically, we first leverage recent results on non-linear ICA to show that causal models are identifiable from observational data given a causal ordering, and thus can be recovered using autoregressive normalizing flows (NFs). Second, we analyse different design and learning choices for causal normalizing flows to capture the underlying causal data-generating process. Third, we describe how to implement the do-operator in causal NFs, and thus, how to answer interventional and counterfactual questions. Finally, in our experiments, we validate our design and training choices through a comprehensive ablation study; compare causal NFs to other approaches for approximating causal models; and empirically demonstrate that causal NFs can be used to address real-world problems—where mixed discrete-continuous data and partial knowledge on the causal graph is the norm. The code for this work can be found at https://***/psanch21/causal-flows.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GSLB: The Graph Structure Learning Benchmark 37

GSLB: The Graph Structure Learning Benchmark

引用

37th Conference on Neural Information Processing systems, NeurIPS 2023

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

ISBN: (纸本)9781713899921

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Human-centered AI and robotics

引用

AI Perspectives 2022年第1期4卷 1-14页

作者： Doncieux, Stephane Chatila, Raja Straube, Sirko Kirchner, Frank Institute of Intelligent Systems and Robotics (ISIR) Sorbonne Université CNRS Paris France Robotics Innovation Center DFKI GmbH (German Research Center for Artificial Intelligence) Bremen Germany Faculty of Mathematics and Computer Science Robotics Group University of Bremen Bremen Germany

robotics has a special place in AI as robots are connected to the real world and robots increasingly appear in humans everyday environment, from home to industry. Apart from cases were robots are expected to completely replace them, humans will largely benefit from real interactions with such robots. This is not only true for complex interaction scenarios like robots serving as guides, companions or members in a team, but also for more predefined functions like autonomous transport of people or goods. More and more, robots need suitable interfaces to interact with humans in a way that humans feel comfortable and that takes into account the need for a certain transparency about actions taken. The paper describes the requirements and state-of-the-art for a human-centered robotics research and development, including verbal and non-verbal interaction, understanding and learning from each other, as well as ethical questions that have to be dealt with if robots will be included in our everyday environment, influencing human life and societies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Application of Machine Learning: Detecting Errors in Network Simulations 22

A New Application of Machine Learning: Detecting Errors in N...

引用

Proceedings of the Winter Simulation Conference

作者： Maciej K. Wozniak Luke Liang Hieu Phan Philippe J. Giabbanelli Department of Intelligent Systems KTH Royal Institute of Technology Stockholm SWEDEN Department of Computer Science & Software Engineering Miami University Oxford OH USA

After designing a simulation and running it locally on a small network instance, the implementation can be scaled-up via parallel and distributed computing (e.g., a cluster) to cope with massive networks. However, implementation changes can create errors (e.g., parallelism errors), which are difficult to identify since the aggregate behavior of an incorrect implementation of a stochastic network simulation can fall within the distributions expected from correct implementations. In this paper, we propose the first approach that applies machine learning to traces of network simulations to detect errors. Our technique transforms simulation traces into images by reordering the network's adjacency matrix, and then training supervised machine learning models. Our evaluation on three simulation models shows that we can easily detect previously encountered types of errors and even confidently detect new errors. This work opens up numerous opportunities by examining other simulation models, representations (i.e., matrix reordering algorithms), or machine learning techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Online Multi-Contact Feedback Model Predictive Control for Interactive Robotic Tasks

Online Multi-Contact Feedback Model Predictive Control for I...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Seo Wook Han Maged Iskandar Jinoh Lee Min Jun Kim Intelligent Robotic Systems Laboratory Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea Institute of Robotics and Mechatronics German Aerospace Center (DLR) Wessling Germany Department of Mechanical Engineering KAIST Daejeon Republic of Korea

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In this paper, we propose a model predictive control (MPC) that accomplishes interactive robotic tasks, in which multiple contacts may occur at unknown locations. To address such scenarios, we made an explicit contact feedback loop in the MPC framework. An algorithm called Multi-Contact Particle Filter with Exploration Particle (MCP-EP) is employed to establish real-time feedback of multi-contact information. Then the interaction locations and forces are accommodated in the MPC framework via a spring contact model. Moreover, we achieved real-time control for a 7 degrees of freedom robot without any simplifying assumptions by employing a Differential-Dynamic-Programming algorithm. We achieved 6.8kHz, 1.9kHz, and 1.8kHz update rates of the MPC for 0, 1, and 2 contacts, respectively. This allows the robot to handle unexpected contacts in real time. Real-world experiments show the effectiveness of the proposed method in various scenarios.

关键词： Feedback loop Prediction algorithms Real-time systems Particle filters Task analysis Springs Robots

来源：评论

学校读者我要写书评

暂无评论

Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling

arXiv

引用

arXiv 2023年

作者： Hollenstein, Jakob Martius, Georg Piater, Justus Department of Computer Science University of Innsbruck Austria Digital Science Center University of Innsbruck Austria Max Planck Institute for Intelligent Systems Tübingen Germany Department of Computer Science University of Tübingen Germany

Proximal Policy Optimization (PPO), a popular on-policy deep reinforcement learning method, employs a stochastic policy for exploration. In this paper, we propose a colored noise-based stochastic policy variant of PPO. Previous research highlighted the importance of temporal correlation in action noise for effective exploration in off-policy reinforcement learning. Building on this, we investigate whether correlated noise can also enhance exploration in on-policy methods like PPO. We discovered that correlated noise for action selection improves learning performance and outperforms the currently popular uncorrelated white noise approach in on-policy methods. Unlike off-policy learning, where pink noise was found to be highly effective, we found that a colored noise, intermediate between white and pink, performed best for on-policy learning in PPO. We examined the impact of varying the amount of data collected for each update by modifying the number of parallel simulation environments for data collection and observed that with a larger number of parallel environments, more strongly correlated noise is beneficial. Due to the significant impact and ease of implementation, we recommend switching to correlated noise as the default noise source in PPO. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Image Clustering by Spiking Neural Networks

Deep Image Clustering by Spiking Neural Networks

引用

Applied Imagery Pattern Recognition Workshop (AIPR)

作者： Arash Mahyari Hadi AliAkbarpour Florida Institute For Human and Machine Cognition (IHMC) Pensacola FL USA Department of Intelligent Systems and Robotics University of West Florida Pensacola FL USA Department of Computer Science Saint Louis University St. Louis MO USA

Neuromorphic cameras, or event cameras, are biologically-inspired sensors that detect changes in illumination at a pixel level, different from traditional cameras where each pixel independently and asynchronously outputs when it senses illumination changes. The neuromorphic cameras exhibit high-temporal resolution and dynamic range, useful in various applications. Spiking Neural Networks (SNNs), mimicking biological neurons, are efficient in processing neuromorphic images due to their event-driven, low-power nature. However, training SNNs is challenging because of the non-differentiability of neuron models which require different optimization techniques. Inspired by recent works on unsupervised deep clustering in conventional deep learning, we introduce a novel deep clustering algorithm that employs SNNs to extract and group visual features from neuromorphic images into clusters. It utilizes an SNN feature extractor for neuromorphic images, grouping the extracted features using K-means clustering. This algorithm, which doesn’t require pre-trained SNN weights, alternates between cluster updates and SNN weight adjustments. The extracted feature vectors in SNN are clustered and used as pseudo-labels for supervised training of the SNN extractor. The performance of the proposed algorithm is evaluated on two datasets of MNIST and NMNIST, and its effectiveness is assessed using the Normalized Mutual Information (NMI) metric. The performance of our SNN system with neuromorphic images, while marginally below its counterparts of ANNs with traditional images, demonstrates considerable potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalized Interpolating Discrete Diffusion

arXiv

引用

arXiv 2025年

作者： Rütte, Dimitri Von Fluri, Janis Ding, Yuhui Orvieto, Antonio Schölkopf, Bernhard Hofmann, Thomas Data Analytics Lab Department of Computer Science ETH Zurich Switzerland ELLIS Institute Tübingen Tübingen AI Center Germany Max Planck Institute for Intelligent Systems Tübingen Germany

While state-of-the-art language models achieve impressive results through next-token prediction, they have inherent limitations such as the inability to revise already generated tokens. This has prompted exploration of alternative approaches such as discrete diffusion. However, masked diffusion, which has emerged as a popular choice due to its simplicity and effectiveness, reintroduces this inability to revise words. To overcome this, we generalize masked diffusion and derive the theoretical backbone of a family of general interpolating discrete diffusion (GIDD) processes offering greater flexibility in the design of the noising processes. Leveraging a novel diffusion ELBO, we achieve compute-matched state-of-the-art performance in diffusion language modeling. Exploiting GIDD’s flexibility, we explore a hybrid approach combining masking and uniform noise, leading to improved sample quality and unlocking the ability for the model to correct its own mistakes, an area where autoregressive models notoriously have struggled. Our code and models are open-source: https://***/dvruette/gidd/ © 2025, CC BY.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of LLM-based Chatbots for Task Scheduling in Robot Operations

Exploring the Potential of LLM-based Chatbots for Task Sched...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： Catarina Rema Armando Sousa Heber Sobreira Pedro Costa Manuel F. Silva CRIIS - Centre for Robotics in Industry and Intelligent Systems INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal Faculty of Engineering University of Porto (FEUP) Porto Portugal ISEP Polytechnic of Porto rua Dr. António Bernardino de Almeida Porto Portugal

ISBN: (数字)9798331538606

ISBN: (纸本)9798331538613

The rise of Industry 4.0 has revolutionized manufacturing by integrating real-time data analysis, artificial intelligence (AI), automation, and interconnected systems, enabling adaptive and resilient smart factories. Autonomous Mobile Robots (AMRs), with their advanced mobility and navigation capabilities, are a pillar of this transformation. However, their deployment in job shop environments adds complexity to the already challenging Job Shop Scheduling Problem (JSSP), expanding it to include task allocation, robot scheduling, and travel time optimization, creating a multi-faceted, non-deterministic polynomial-time hardness (NP-hard) problem. Traditional approaches such as heuristics, meta-heuristics, and mixed integer linear programming (MILP) are commonly used. Recent AI advancements, particularly large language models (LLM), have shown potential in addressing these scheduling challenges due to significant improvements in reasoning and decision-making from textual data. This paper examines the application of LLM to tackle scheduling complexities in smart job shops with mobile robots. Guided by tailored prompts inserted manually, LLM are employed to generate scheduling solutions, being these compared to an heuristic-based method. The results indicate that LLM currently have limitations in solving complex combinatorial problems, such as task scheduling with mobile robots. Due to issues with consistency and repeatability, they are not yet reliable enough for practical implementation in industrial environments. However, they offer a promising foundation for augmenting traditional approaches in the future.

关键词： Job shop scheduling Service robots Large language models Chatbots Real-time systems Mobile robots Resource management Reliability Autonomous robots Smart manufacturing

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：