检索结果-内蒙古大学图书馆

Beyond game environments: Evolutionary algorithms with parameter space noise for task-oriented dialogue policy exploration

引用

Neurocomputing 2025年 648卷

作者： Qingxin Xiao Yangyang Zhao Lingwei Dang Yun Hao Le Che Qingyao Wu South China University of Technology School of Software Engineering Guangzhou 510006 Guangdong PR China Institute for Super Robotics(Huangpu) Guangzhou 510700 Guangdong PR China Changsha University of Science and Technology School of Computer and Communication Engineering Changsha 410114 Hunan PR China South China University of Technology School of Architecture Guangzhou 510006 Guangdong PR China

Reinforcement learning (RL) has achieved significant success in task-oriented dialogue (TOD) policy learning. Nevertheless, training dialogue policy through RL faces a critical challenge: insufficient exploration, which leads to the policy getting trapped in local optima. Evolutionary algorithms (EAs) enhance exploration breadth by maintaining and selecting diverse individuals, and they often add parameter space noise among different individuals to simulate mutation, thereby increasing exploration depth. This approach has proven to be an effective method for enhancing RL exploration and has shown promising results in game domains. However, previous research has not analyzed its effectiveness in TOD dialogue policy. Given the substantial differences between gaming contexts and TOD dialogue policy, this paper explores and validates the efficacy of EAs in TOD dialogue policy, investigating the effects of different evolutionary cycles and various noise strategies across different dialogue tasks to determine which combination of evolutionary cycle and noise strategy is most suitable for TOD dialogue policy. Additionally, we propose an adaptive noise evolution method that dynamically adjusts noise scales to improve exploration efficiency. Experiments on the MultiWOZ dataset demonstrate significant performance improvements, achieving state-of-the-art results in both on-policy and off-policy settings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Ant Colony System for Multi-Robot Task Allocation with Large-scale Cooperative Tasks and Precedence Constraints

An Efficient Ant Colony System for Multi-Robot Task Allocati...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Xiao-Fang Liu Bo-Cheng Lin Zhi-Hui Zhan Sang-Woon Jeon Jun Zhang Institute of Robotics and Automatic Information System College of Artificial Intelligence Nankai University Tianjin China Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin China School of Computer Science and Engineering South China University of Technology Guangzhou China Hanyang University Ansan South Korea Chaoyang University of Technology Taichung Taiwan China

ISBN: (纸本)9781728190495

Multiple heterogeneous robots can work together to execute complex tasks. Given multiple heterogeneous tasks and heterogeneous robots, the allocation of tasks to robots is a challenging optimization problem. Lots of methods have been proposed for the multi-robot task allocation (MRTA) problem. However, most existing methods only consider small-scale tasks without precedence constraints. Hence, this paper tracks the time-extended MRTA problem with large-scale cooperative tasks and precedence constraints, and proposes an efficient ant colony system (ACS) to solve the problem. In the proposed algorithm, we adopt a permutation with task-robot alliance pairs as the encode scheme to represent a feasible solution. A pheromone matrix is initialized by a hierarchical greedy strategy and iteratively updated to record historical experience. Heuristic information related to the optimization objective is also designed to help algorithm find better solutions according to the current state. Through combining pheromone and heuristic information, the ACS is able to search high-quality solutions from a global perspective. Experimental results on multiple problem instances are reported to show the advantage of the proposed method. The proposed ACS method can well solve the MRTA problem with large-scale cooperative tasks and precedence constraints.

关键词： Processor scheduling Heuristic algorithms Resource management Task analysis Robots Optimization Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Learning Enhanced Resolution-Wise Features For Human Pose Estimation

Learning Enhanced Resolution-Wise Features For Human Pose Es...

引用

IEEE International Conference on Image Processing

作者： Kun. Zhang Peng He Ping Yao Ge Chen Rui Wu Min Du Huimin Li Li Fu Tianyao Zheng Chinese Academy of Sciences Institute of Computing Technology School of Computer Science and Technology University of Chinese Academy of Sciences Horizon Robotics School of Automation Beijing Institute of Technology

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

Recently, multi-resolution networks (such as Hourglass, CPN, HRNet, etc.) have achieved significant performance on pose estimation by combining feature maps of various resolutions. In this paper, we propose a Resolution-wise Attention Module (RAM) and Gradual Pyramid Refinement (GPR), to learn enhanced resolution-wise feature maps for precise pose estimation. Specifically, RAM learns a group of weights to represent the different importance of feature maps across resolutions, and the GPR gradually merges every two feature maps from low to high resolutions to regress final human keypoint heatmaps. With the enhanced resolution-wise features learnt by CNN, we obtain more accurate human keypoint locations. The efficacies of our proposed methods are demonstrated on MS-COCO dataset, achieving state-of-the-art performance with average precision of 77.7 on COCO va12017 set and 77.0 on test-dev2017 set without using extra human keypoint training dataset.

关键词： Pose estimation Heating systems Ground penetrating radar Feature extraction Random access memory Training Task analysis

来源：评论

学校读者我要写书评

暂无评论

Learning to solve hard minimal problems

arXiv

引用

arXiv 2021年

作者： Hruby, Petr Duff, Timothy Leykin, Anton Pajdla, Tomas ETH Zürich Department of Computer Science University of Washington Department of Mathematics United States Georgia Institute of Technology School of Mathematics Czech Technical University in Prague Czech Institute of Informatics Robotics and Cybernetics Czech Republic

We present an approach to solving hard geometric optimization problems in the RANSAC framework. The hard minimal problems arise from relaxing the original geometric optimization problem into a minimal problem with many spurious solutions. Our approach avoids computing large numbers of spurious solutions. We design a learning strategy for selecting a starting problem-solution pair that can be numerically continued to the problem and the solution of interest. We demonstrate our approach by developing a RANSAC solver for the problem of computing the relative pose of three calibrated cameras, via a minimal relaxation using four points in each view. On average, we can solve a single problem in under 70 µs. We also benchmark and study our engineering choices on the very familiar problem of computing the relative pose of two calibrated cameras, via the minimal case of five points in two *** Codes 65H20, 68T45 © 2021, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Image super-resolution with an enhanced group convolutional neural network

arXiv

引用

arXiv 2022年

作者： Tian, Chunwei Yuan, Yixuan Zhang, Shichao Lin, Chia-Wen Zuo, Wangmeng Zhang, David School of Software Northwestern Polytechnical University Shaanxi Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China Department of Electrical Engineering City University of Hong Kong Hong Kong School of Computer Science and Engineering Central South University Hunan Changsha410083 China Department of Electrical Engineering the Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China Peng Cheng Laboratory Guangdong Shenzhen518055 China Guangdong Shenzhen518172 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. However, CNNs depend on deeper network architectures to improve performance of image super-resolution, which may increase computational cost in general. In this paper, we present an enhanced super-resolution group CNN (ESRGCNN) with a shallow architecture by fully fusing deep and wide channel features to extract more accurate low-frequency information in terms of correlations of different channels in single image super-resolution (SISR). Also, a signal enhancement operation in the ESRGCNN is useful to inherit more long-distance contextual information for resolving long-term dependency. An adaptive up-sampling operation is gathered into a CNN to obtain an image super-resolution model with low-resolution images of different sizes. Extensive experiments report that our ESRGCNN surpasses the state-of-the-arts in terms of SISR performance, complexity, execution speed, image quality evaluation and visual effect in SISR. Code is found at https://***/hellloxiaotian/ESRGCNN. Copyright © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Lazy lifelong planning for efficient replanning in graphs with expensive edge evaluation

arXiv

引用

arXiv 2021年

作者： Lim, Jaein Srinivasa, Siddhartha Tsiotras, Panagiotis School of Aerospace Engineering Georgia Institute of Technology AtlantaGA30332-0150 United States School of Computer Science & Engineering University of Washington SeattleWA98195-2355 United States School of Aerospace Engineering Institute for Robotics Intelligent Machines Georgia Institute of Technology AtlantaGA30332-0150 United States

We present an incremental search algorithm, called Lifelong-GLS, which combines the vertex efficiency of Lifelong Planning A* (LPA*) and the edge efficiency of Generalized Lazy Search (GLS) for efficient replanning on dynamic graphs where edge evaluation is expensive. We use a lazily evaluated LPA* to repair the cost-to-come inconsistencies of the relevant region of the current search tree based on the previous search results, and then we restrict the expensive edge evaluations only to the current shortest subpath as in the GLS framework. The proposed algorithm is complete and correct in finding the optimal solution in the current graph, if one exists. We also show that the search returns a bounded suboptimal solution, if an inflated heuristic edge weight is used and the tree repairing propagation is truncated early for faster search. Finally, we show the efficiency of the proposed algorithm compared to the standard LPA* and the GLS algorithms over consecutive search episodes in a dynamic environment. For each search, the proposed algorithm reduces the edge evaluations by a significant amount compared to the LPA*. Both the number of vertex expansions and the number of edge evaluations are reduced substantially compared to GLS, as the proposed algorithm utilizes previous search results to facilitate the new search. Copyright © 2021, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Neuro-Fuzzy Control Approach for Robot's Trajectory Tracking

Design and Implementation of Neuro-Fuzzy Control Approach fo...

引用

International conference of Electronics, Communication and Aerospace technology (ICECA)

作者： Kiruba Sandou D Sunad kumara A N Binod Kumar Choudhary Shashikala Gurpur Sarishma Natrayan L M. SivaramKumar Department of Robotics and Automation Manakula Vinayagar Institute of Technology Pondicherry India Department of Computer Science and Engineering BGS Institute of Technology Adichunchanagiri University Mandya Karnataka India Department of Electrical and Electronics Engineering ARKA Jain University Jamshedpur Jharkhand India Faculty of Law Symbiosis Law School (SLS) Symbiosis International (Deemed University) (SIU) Pune Maharashtra India Department of Management Studies Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai Tamilnadu India Department of EEE Karpagam Academy of higher education Coimbatore Tamiinadu

Achieving precise trajectory tracking while minimizing errors, reducing settling time, and curbing overshoot presents a significant challenge in the domain of robot-manipulator control. In response, this paper proposes a novel controller design for robot manipulators, incorporating two distinct approaches: a conventional fuzzy controller and an advanced Neuro-Fuzzy controller. These controllers are tailored to elevate trajectory tracking performance by simultaneously optimizing time characteristics in robot manipulator responses. To assess their efficacy, a range of test scenarios is devised, encompassing different trajectory types, including linear and nonlinear paths. Upon comparative analysis, the results highlight an intriguing contrast: while the fuzzy controller exhibits higher maximum overshoot and longer settling times in the robot's response, the Neuro-Fuzzy controller consistently demonstrates superior performance. The comprehensive error analysis such as Integral Square Error (ISE) and Integral Absolute Error (IAE) further underscores the capability of the Neuro-Fuzzy-based robot manipulator in delivering trajectory tracking precision. This study contributes to the advancement of trajectory control techniques for robot manipulators, paving the way for enhanced automation and performance across various applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A bottom-up paradigm for traffic scene graph representation 9

A bottom-up paradigm for traffic scene graph representation

引用

9th International Conference on Computing and Pattern Recognition, ICCPR 2020

作者： Zhang, Zhixuan Zhang, Chi Liu, Yuehu Su, Yuanqi Li, Ping Zheng, Jinzi School of Software Engineering Xi'An Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'An Jiaotong University Xi'an China Shaanxi Key Lab of Digital Technology and Intelligent Systems Xi'an China School of Computer Science and Technology Xi'An Jiaotong University Xi'an China China Academy of Railway Sciences Corporation Limited Beijing China

ISBN: (纸本)9781450387835

With increasing hardware computing power and model capacity, visual tasks for scene cognitive understanding have attracted more attention, such as visual relationships inference. The scene graph representation formed by a coupling of objects, attributes and relationships nodes displayed by different modalities of information, including original image, foreground things, background stuff and scene attributes, strongly promotes the progress of research area. In this paper, we address the scene graph representation of traffic scenarios for autonomous driving. It should be noted that the universal representation are the specific needs of cognitive understanding of traffic scenes: on the one hand, there is a lack of fine-grained description of key objects and attributes;on the other hand, there are redundant descriptions of objects and relationships. To tackle these problems, we take advantage of the fine-grained instance-level annotation of the traffic scene, proposing a bottom-up representation paradigm. It makes full use of the hierarchical structure of the traffic scene and the sparsity of element classes. In addition, on the basis of the existing methods, we optimize the relationship list of traffic scene graph representation. Moreover, we improve the scene graph annotation methods, proposing a "ground-vision joint location method"to better describe the spatially-distributed visual knowledge. The case analysis showed that compared with existing methods, our paradigm for scene graph can represent more abundant traffic scene information. © 2020 ACM.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Overcoming the Fear of the Dark: Occlusion-Aware Model-Predictive Planning for Automated Vehicles Using Risk Fields

arXiv

引用

arXiv 2023年

作者： van der Ploeg, Chris Nyberg, Truls Sánchez, José Manuel Gaspar Silvas, Emilia van de Wouw, Nathan Netherlands Organisation for Applied Scientific Research Integrated Vehicle Safety Group Helmond5700 AT Netherlands Eindhoven University of Technology Dynamics and Control Group Mechanical Engineering Dept. P.O. Box 513 Eindhoven5600 MB Netherlands Eindhoven University of Technology Control Systems Technology Group Mechanical Engineering Dept. P.O. Box 513 Eindhoven5600 MB Netherlands KTH Royal Institute of Technology Division of Robotics Perception and Learning School of Electrical Engineering and Computer Science Stockholm100 44 Sweden Scania CV AB Södertälje151 87 Sweden

As vehicle automation advances, motion planning algorithms face escalating challenges in achieving safe and efficient navigation. Existing Advanced Driver Assistance Systems (ADAS) primarily focus on basic tasks, leaving unexpected scenarios for human intervention, which can be error-prone. Motion planning approaches for higher levels of automation in the state-of-the-art are primarily oriented toward the use of risk- or anti-collision constraints, using over-approximates of the shapes and sizes of other road users to prevent collisions. These methods however suffer from conservative behavior and the risk of infeasibility in high-risk initial conditions. In contrast, our work introduces a novel multi-objective trajectory generation approach. We propose an innovative method for constructing risk fields that accommodates diverse entity shapes and sizes, which allows us to also account for the presence of potentially occluded objects. This methodology is integrated into an occlusion-aware trajectory generator, enabling dynamic and safe maneuvering through intricate environments while anticipating (potentially hidden) road users and traveling along the infrastructure toward a specific goal. Through theoretical underpinnings and simulations, we validate the effectiveness of our approach. This paper bridges crucial gaps in motion planning for automated vehicles, offering a pathway toward safer and more adaptable autonomous navigation in complex urban contexts. Copyright © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Line Drawing Guided Progressive Inpainting of Mural Damage

arXiv

引用

arXiv 2022年

作者： Li, Luxi Zou, Qin Zhang, Fan Yu, Hongkai Chen, Long Song, Chengfang Huang, Xianfeng Wang, Xiaoguang Li, Qingquan Department of Computer Science Technology United International College of Beijing Normal University HongKong Baptist University Zhuhai China Machine Vision and Robotics Laboratory School of Computer Science Wuhan University Wuhan China State Key Laboratory of Surveying Mapping and Remote Sensing Information Engineering Wuhan University Wuhan China Department of Electrical Engineering and Computer Science Cleveland State University OH United States Institute of Automation Chinese Academy of Sciences Beijing China Cultural Heritage Intelligent Computing Laboratory Wuhan University Wuhan China Guangming Laboratory Shenzhen University Shenzhen China

Mural image inpainting is far less explored compared to its natural image counterpart and remains largely unsolved. Most existing image-inpainting methods tend to take the target image as the only input and directly repair the damage to generate a visually plausible result. These methods obtain high performance in restoration or completion of some pre-defined objects, e.g., human face, fabric texture, and printed texts, etc., however, are not suitable for repairing murals with varying subjects and large damaged areas. Moreover, due to discrete colors in paints, mural inpainting may suffer from apparent color bias. To this end, in this paper, we propose a line drawing guided progressive mural inpainting method. It divides the inpainting process into two steps: structure reconstruction and color correction, implemented by a structure reconstruction network (SRN) and a color correction network (CCN), respectively. In structure reconstruction, SRN utilizes the line drawing as an assistant to achieve large-scale content authenticity and structural stability. In color correction, CCN operates a local color adjustment for missing pixels which reduces the negative effects of color bias and edge jumping. The proposed approach is evaluated against the current state-of-the-art image inpainting methods. Qualitative and quantitative results demonstrate the superiority of the proposed method in mural image inpainting. The codes and data are available at https://***/qinnzou/mural-image-inpainting . © 2022, CC BY-NC-ND.

关键词： Restoration

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：