检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kuang, Haofei Pan, Yue Zhong, Xingguang Wiesmann, Louis Behley, Jens Stachniss, Cyrill Center for Robotics University of Bonn Germany Department of Engineering Science University of Oxford United Kingdom Lamarr Institute for Machine Learning and Artificial Intelligence Germany

Globally localizing a mobile robot in a known map is often a foundation for enabling robots to navigate and operate autonomously. In indoor environments, traditional Monte Carlo localization based on occupancy grid maps is considered the gold standard, but its accuracy is limited by the representation capabilities of the occupancy grid map. In this paper, we address the problem of building an effective map representation that allows to accurately perform probabilistic global localization. To this end, we propose an implicit neural map representation that is able to capture positional and directional geometric features from 2D LiDAR scans to efficiently represent the environment and learn a neural network that is able to predict both, the non-projective signed distance and a direction-aware projective distance for an arbitrary point in the mapped environment. This combination of neural map representation with a lightweight neural network allows us to design an efficient observation model within a conventional Monte Carlo localization framework for pose estimation of a robot in real time. We evaluated our approach to indoor localization on a publicly available dataset for global localization and the experimental results indicate that our approach is able to more accurately localize a mobile robot than other localization approaches employing occupancy or existing neural map representations. In contrast to other approaches employing an implicit neural map representation for 2D LiDAR localization, our approach allows to perform real-time pose tracking after convergence and near real-time global localization. The code of our approach is available at: https://***/PRBonn/enm-mcl. Copyright © 2025, The Authors. 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

Negotiating systemic racial and gender bias as a minoritized adult design researcher 21

Negotiating systemic racial and gender bias as a minoritized...

引用

8th ACM SIGCHI Annual Symposium on Computer-Human Interaction in Play, CHI PLAY 2021

作者： Odili Uchidiuno, Judith Solyst, Jaemarie Kemper, Jonaya Harpstead, Erik Higashi, Ross Hammer, Jessica National Robotics Engineering Center Carnegie Mellon University United States Human-Computer Interaction Institute Carnegie Mellon University United States

ISBN: (纸本)9781450383561

Fostering equal design partnerships in adult-child codesign interactions is a well-documented challenge in HCI. It is assumed that adults come into these interactions with power and have to make adjustments to allow childrens' input to be equally valued. However, power is not a unilateral construct - it is in part determined by social and cultural norms that often disadvantage minoritized groups. Striving for equal partnership without centering users' and participants' intersectional identities may lead to unproductive adult-child codesign interactions. We codesigned a game, primarily facilitated by a black woman researcher, with K-5 afterschool programs comprised of students from three different communities - a middle-class, racially diverse community;a low-income, primarily African American community;and a working-class rural, white, community over a period of 20 weeks. We share preliminary insights on how racial and gender biases affect codesign partnerships and describe future research plans to modify our program structure to foster more effective adult-child interactions. © 2021 Owner/Author.

关键词： Mergers and acquisitions

来源：评论

学校读者我要写书评

暂无评论

Breaking through the learning plateaus of in-context learning in transformer 24

Breaking through the learning plateaus of in-context learnin...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Jingwen Fu Tao Yang Yuwang Wang Yan Lu Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Tsinghua University Microsoft Research Asia

In-context learning, i.e., learning from context examples, is an impressive ability of Transformer. Training Transformers to possess this in-context learning skill is computationally intensive due to the occurrence of learning plateaus, which are periods within the training process where there is minimal or no enhancement in the model's incontext learning capability. To study the mechanism behind the learning plateaus, we conceptually separate a component within the model's internal representation that is exclusively affected by the model's weights. We call this the "weights component", and the remainder is identified as the "context component". By conducting meticulous and controlled experiments on synthetic tasks, we note that the persistence of learning plateaus correlates with compromised functionality of the weights component. Recognizing the impaired performance of the weights component as a fundamental behavior that drives learning plateaus, we have developed three strategies to expedite the learning of Transformers. The effectiveness of these strategies is further confirmed in natural language processing tasks. In conclusion, our research demonstrates the feasibility of cultivating a powerful in-context learning ability within AI systems in an eco-friendly manner.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Path Loss Modelling for UAV Communications in Urban Scenarios with Random Obstacles

Path Loss Modelling for UAV Communications in Urban Scenario...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Abdul Saboor Zhuangzhuang Cui Evgenii Vinogradov Sofie Pollin WaveCoRE of the Department of Electrical Engineering (ESAT) KU Leuven Leuven Belgium Autonomous Robotics Research Center Technology Innovation Institute Abu Dhabi UAE

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

Path Loss ( $PL$ ) is vital to evaluate the performance of Unmanned Aerial Vehicles (UAVs) as Aerial Base Stations (ABSs), particularly in urban environments with complex propagation due to various obstacles. Accurately modeling $PL$ requires a generalized Probability of Line-of-Sight $(P_{LoS})$ that can consider multiple obstructions. While the existing $P_{LoS}$ models mostly assume a simplified Manhattan grid with uniform building sizes and spacing, they overlook the real-world variability in building dimensions. Furthermore, such models do not consider other obstacles, such as trees and streetlights, which may also impact the performance, especially in millimeter-wave (mmWave) bands. This paper introduces a Manhattan Random Simulator (MRS) to estimate $P_{LoS}$ for UAV-based communications in urban areas by incorporating irregular building shapes, non-uniform spacing, and additional random obstacles to create a more realistic environment. Lastly, we present the PL differences with and without obstacles for standard urban environments and derive the empirical PL for these environments.

关键词： Base stations Shape Urban areas Buildings Layout Line-of-sight propagation Autonomous aerial vehicles Propagation losses Millimeter wave communication Standards

来源：评论

学校读者我要写书评

暂无评论

A Novel Cable-Driven Soft Robot for Surgery

引用

Journal of Shanghai Jiaotong university(Science) 2024年第1期29卷 60-72页

作者：李茹陈方俞文伟 IGARASH Tatsuo 舒雄鹏谢叻 Institute of Forming Technology and Equipment School of Materials Science and EngineeringShanghai Jiao Tong UniversityShanghai 200030China The Sixth People's Hospital Affiliated to Shanghai Jiao Tong University Shanghai 200233China Center for Frontier Medical Engineering Chiba UniversityChiba 263-8522Japan Seirei Sakura Citizen Hospital Chiba 285-8765Japan Institute of Medical Robotics Shanghai Jiao Tong UniversityShanghai 200030China School of Mathematics and Computer Science Quanzhou Normal UniversityQuanzhou 362000FujianChina

Robot-assisted laparoscopic radical prostatectomy(RARP)is widely used to treat prostate *** rigid instruments primarily used in RARP cannot overcome the problem of blind areas in surgery and lead to more trauma such as more incision for the passage of the instrument and additional tissue damage caused by rigid *** robots are relatively fexible and theoretically have infinite degrees of freedom which can overcome the problem of the rigid instrument.A soft robot system for single-port transvesical robot-assisted radical prostatectomy(STvRARP)is developed in this *** soft manipulator with 10 mm in diameter and a maximum bending angle of 270°has good fexibility and *** design and mechanical structure of the soft robot are *** kinematics of the soft manipulator is established and the inverse kinematics is compensated based on the characteristics of the designed soft *** master-slave control system of soft robot for surgery is built and the feasibility of the designed soft robot is verified.

关键词： soft robot kinematics model robot-assisted surgery

来源：评论

学校读者我要写书评

暂无评论

LOID: Lane Occlusion Inpainting and Detection for Enhanced Autonomous Driving Systems

arXiv

引用

arXiv 2024年

作者： Agrawal, Aayush Sivakumar, Ashmitha Jaysi Kaif, Ibrahim Banerjee, Chayan Team Abhiyaan Center For Innovation Indian Institute of Technology Madras India School of Electrical Engineering and Robotics Queensland University of Technology Brisbane Australia

Accurate lane detection is essential for effective path planning and lane following in autonomous driving, especially in scenarios with significant occlusion from vehicles and pedestrians. Existing models often struggle under such conditions, leading to unreliable navigation and safety risks. We propose two innovative approaches to enhance lane detection in these challenging environments, each showing notable improvements over current methods. The first approach aug-Segment improves conventional lane detection models by augmenting the training dataset of CULanes with simulated occlusions and training a segmentation model. This method achieves a 12% improvement over a number of SOTA models on the CULanes dataset, demonstrating that enriched training data can better handle occlusions, however, since this model lacked robustness to certain settings, our main contribution is the second approach, LOID Lane Occlusion Inpainting and Detection. LOID introduces an advanced lane detection network that uses an image processing pipeline to identify and mask occlusions. It then employs inpainting models to reconstruct the road environment in the occluded areas. The enhanced image is processed by a lane detection algorithm, resulting in a 20% & 24% improvement over several SOTA models on the BDDK100 and CULanes datasets respectively, highlighting the effectiveness of this novel technique. © 2024, CC BY-NC-ND.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Semantic-aware Representation Learning for Homography Estimation

arXiv

引用

arXiv 2024年

作者： Liu, Yuhan Huang, Qianxin Hui, Siqi Fu, Jingwen Zhou, Sanping Wu, Kangyi Li, Pengna Wang, Jinjun National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China Huawei Inc. China

Homography estimation is the task of determining the transformation from an image pair. Our approach focuses on employing detector-free feature matching methods to address this issue. Previous work has underscored the importance of incorporating semantic information, however there still lacks an efficient way to utilize semantic information. Previous methods suffer from treating the semantics as a pre-processing, causing the utilization of semantics overly coarse-grained and lack adaptability when dealing with different tasks. In our work, we seek another way to use the semantic information, that is semantic-aware feature representation learning framework. Based on this, we propose SRMatcher, a new detector-free feature matching method, which encourages the network to learn integrated semantic feature representation. Specifically, to capture precise and rich semantics, we leverage the capabilities of recently popularized vision foundation models (VFMs) trained on extensive datasets. Then, a cross-images Semantic-aware Fusion Block (SFB) is proposed to integrate its fine-grained semantic features into the feature representation space. In this way, by reducing errors stemming from semantic inconsistencies in matching pairs, our proposed SRMatcher is able to deliver more accurate and realistic outcomes. Extensive experiments show that SRMatcher surpasses solid baselines and attains SOTA results on multiple real-world datasets. Compared to the previous SOTA approach GeoFormer, SRMatcher increases the area under the cumulative curve (AUC) by about 11% on HPatches. Additionally, the SRMatcher could serve as a plug-and-play framework for other matching methods like LoFTR, yielding substantial precision improvement. Code is available at https://***/lyh200095/SRMatcher. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Novel Aerial-Aquatic Locomotion Robot with Variable Stiffness Propulsion Module

arXiv

引用

arXiv 2024年

作者： Hu, Junzhe Chen, Pengyu Feng, Tianxiang Wen, Yuxuan Wu, Ke Dong, Janet The UC Center for Robotics Research College of Engineering and Applied Science University of Cincinnati CincinnatiOH United States The Robotics Institute School of Computer Science Carnegie Mellon University PittsburghPA United States Robotics department Mohamed bin Zayed University of Artificial Intelligence Masdar City Abu Dhabi United Arab Emirates

In recent years, the development of robots capable of operating in both aerial and aquatic environments has gained significant attention. This study presents the design and fabrication of a novel aerial-aquatic locomotion robot (AALR). Inspired by the diving beetle, the AALR incorporates a biomimetic propulsion mechanism with power and recovery strokes. The variable stiffness propulsion module (VSPM) uses low melting point alloy (LMPA) and variable stiffness joints (VSJ) to achieve efficient aquatic locomotion while reduce harm to marine life. The AALR's innovative design integrates the VSPM into the arms of a traditional quadrotor, allowing for effective aerial-aquatic locomotion. The VSPM adjusts joint stiffness through temperature control, meeting locomotion requirements in both aerial and aquatic modes. A dynamic model for the VSPM was developed, with optimized dimensional parameters to increase propulsion force. Experiments focused on aquatic mode analysis and demonstrated the AALR's swimming capability, achieving a maximum swimming speed of 77 mm/s underwater. The results confirm the AALR's effective performance in water environment, highlighting its potential for versatile, eco-friendly operations. Copyright © 2024, The Authors. All rights reserved.

关键词： Aircraft propulsion

来源：评论

学校读者我要写书评

暂无评论

Adaptive Spiking TD3+BC for Offline-to-Online Spiking Reinforcement Learning

Adaptive Spiking TD3+BC for Offline-to-Online Spiking Reinfo...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiangfei Yang Jian Song Xuetao Zhang Donglin Wang School of Engineering Westlake University Hangzhou China National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center of Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Spiking reinforcement learning (SRL) has gradually received attention because of its ultra-low energy consumption, but the current SRL algorithms are almost online algorithms that are sample inefficient. It is well known that pure offline spiking reinforcement (offline RL) learning has limited performance. Therefore, we study SRL in the offline-to-online setting, which simultaneously possesses the advantages of low energy consumption and sample efficiency. To the best of our knowledge, this is the first study for offline-to-online SRL. Like offline-to-online RL, offline-to-online SRL also has the policy collapse issue. To overcome this problem, we adaptively adjust the penalty of behavior cloning term of spiking TD3+BC (SpikTD3+BC) based on the adaptability of policy to environment and propose a stable offline-to-online SRL, named AdaSpikTD3+BC. Experimental results on the D4RL benchmark tasks show that AdaSpikTD3+BC can not only avoid policy collapse but also cost about 10% energy to approach the performance of offline-to-online RL based on DNN.

关键词： Energy consumption Costs Adaptive systems Neural networks Cloning Reinforcement learning Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Combined Coverage and Resource Allocation in UAV-Aided RAN-Slicing 19

Deep Reinforcement Learning for Combined Coverage and Resour...

引用

19th Annual International Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023

作者： Bellone, Lorenzo Galkin, Boris Traversi, Emiliano Natalizio, Enrico Autonomous Robotics Research Center Technology Innovation Institute United Arab Emirates Wireless Communications Group Tyndall National Institute Ireland Université Sorbonne Lipn Umr Cnrs 7030 Paris Nord France Université de Lorraine Loria Umr Cnrs 7503 Nancy France

ISBN: (纸本)9798350346497

Network slicing is a well assessed approach enabling virtualization of the mobile core and radio access network (RAN) in the emerging 5th Generation New Radio. Slicing is of paramount importance when dealing with the emerging and diverse vertical applications entailing heterogeneous sets of requirements. 5G is also envisioning Unmanned Aerial Vehicles (UAVs) to be a key element in the cellular network standard, aiming at their use as aerial base stations and exploiting their flexible and quick deployment to enhance the wireless network performance. This work presents a UAV-assisted 5G network, where the aerial base stations (UAV-BS) are empowered with network slicing capabilities aiming at optimizing the Service Level Agreement (SLA) satisfaction ratio of a set of users. The users belong to three heterogeneous categories of 5G service type, namely, enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), and massive machine-type communication (mMTC). A first application of multi-agent and multi-decision deep reinforcement learning for UAV-BS in a network slicing context is introduced, aiming at the optimization of the SLA satisfaction ratio of users through the joint allocation of radio resources to slices and refinement of the UAV-BSs 2-dimensional trajectories. The performance of the presented strategy have been tested and compared to benchmark heuristics, highlighting a higher percentage of satisfied users (at least 10.5% more) in a variety of scenarios. © 2023 IEEE.

关键词： Reinforcement 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：