检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Ji, Yiming Liu, Yang Xie, Guanghu Ma, Boyu Xie, Zongwu Cao, Baoshi State Key Laboratory of Robotics and System Harbin Institute of Technology Heilongjiang Harbin150001 China

Intelligent autonomous path planning is essential for enhancing the exploration efficiency of mobile robots operating in uneven terrains like planetary surfaces and off-road environments. In this paper, we propose the NNPP model for computing the heuristic region, enabling foundation algorithms like A* to find the optimal path solely within this reduced search space, effectively decreasing the search time. The NNPP model learns semantic information about start and goal locations, as well as map representations, from numerous pre-annotated optimal path demonstrations, and produces a probabilistic distribution over each pixel representing the likelihood of it belonging to an optimal path on the map. More specifically, the paper computes the traversal cost for each grid cell from the slope, roughness and elevation difference obtained from the digital elevation model. Subsequently, the start and goal locations are encoded using a Gaussian distribution and different location encoding parameters are analyzed for their effect on model performance. After training, the NNPP model is able to accelerate path planning on novel maps. Experiments demonstrate that the heuristic region generated by the NNPP model achieves a 3×speedup for optimal path planning under identical hardware conditions. Moreover, the NNPP model’s advantage becomes more pronounced as the size of the map increases. 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

Inverse Kinematics of a Reconfigurable Space Manipulator Based on the Closed-Loop Algorithm

Inverse Kinematics of a Reconfigurable Space Manipulator Bas...

引用

IEEE International Conference on Mechatronics and Automation

作者： Zhiyuan Zhao Xiaohang Yang Zichun Xu Yuntao Li Zhonglai Tian Jingdong Zhao State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin Heilongjiang Province China

This paper investigates a reconfigurable space manipulator’s inverse kinematics (IK) with two lockable passive telescopic links (LPTLs). Depending on these LPTLs’ locking state, the manipulator includes free-space and reconfiguration operation modes. Firstly, we introduce a new ball joint-based solution for the reconfigurable operation mode. Then, we propose an IK simplified method capable of significantly reducing the computational load of the complex inverse differential kinematic (IDK) equations corresponding to the two operation modes. Next, to solve the resulting simplified IDK equations efficiently, we present an IK solution method based on the closed-loop algorithm. This method is developed to resolve the redundancy at the velocity level and can generate highly accurate and smooth trajectory IK solutions that satisfy the joint limit constraints. Finally, we design two typical case studies corresponding to working scenarios of the manipulator during two operation modes. Their simulation results validate the proposed methods’ effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Force Distribution-Based Control Strategy of Landing Gear for the Unmanned Helicopter Landing on the Inclined Surface

Force Distribution-Based Control Strategy of Landing Gear fo...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Tian, Baolin Yu, Haitao Mao, Shihao Cui, Yuxin Yan, Zhen Gao, Haibo Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China College of Electronic Information Engineering Beihang University and the Shanghai Academy of Spaceflight Technology Shanghai China

ISBN: (纸本)9781665481090

The unmanned helicopter plays an important role in the fields of cargo transportation and rescue missions. Due to the limitation of the traditional landing gear structure, the unmanned helicopter has more stringent requirements on the landing terrain. In order to improve the ability to land on the inclined surface for the unmanned helicopter, a novel control strategy of the landing gear based on contact force distribution algorithm is proposed. The overall of landing process includes the desired position tracking stage, the following stage and the attitude adjusting stage. By obtaining the desired acceleration according to the landing and attitude correcting curve of the fuselage, and calculating the desired force based on contact force distribution algorithm, the adaptive motion and trajectory tracking of the landing gear during the landing process has been realized. The simulation results have demonstrated the effectiveness of the strategy when the unmanned helicopter with the initial roll angle of -3 degrees and pitch angle of 3 degrees lands on the inclined surface of 7.07 degrees. In the future, the control strategy can provide a reference for the dynamic landing of the unmanned helicopter while at sea. © 2022 IEEE.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

Research on applicability of containment test data for HPR1000 based on phenomena scaling

International Journal of Advanced Nuclear Reactor Design and...

引用

International Journal of Advanced Nuclear Reactor Design and technology 2025年第2期7卷 120-127页

作者： Yusheng, Liu Xuedong, Qiao Sichao, Tan Jianping, Jing Ting, Wang Yuanbing, Zhu State Environmental Protection Key Laboratory of Nuclear and Radiation Safety Regulatory Simulation and Validation Nuclear and Radiation Safety Center MEE Beijing100086 China Guangdong Provincial Key Laboratory of Nuclear Power Safety Shenzhen518026 China Heilongjiang Provincial Key Laboratory of Nuclear Power System & Equipment Harbin Engineering University Harbin150001 China China Nuclear Power Technology Research Institute Co. Ltd. Shenzhen518026 China

The volume of the nuclear power plant containment is huge, making it difficult to conduct equal-scale or large-scale thermal-hydraulic tests. Currently the test data mainly come from small-scale tests. To address the applicability of small-scale containment test data in validation process of the containment performance analysis code, the analysis method for applicability of experimental data is proposed and developed on the basis of similarity analysis of the pressure response process in the containment. The applicability study of the test data, which are produced by some scaled containment facilities such as the HDR, Battelle and CVTR, is carried out in combination with the test parameters. The applicability of each test case isobtained respectively when they are applied to validate the containment code in case of the Large Break Loss of Coolant Accident (LBLOCA) and Main Steam Line Break Accident (MSLB) of HPR1000 nuclear power plant. The results show that the similarity criteria for pressure response process and key phenomena within the containment vessel under accident conditions can be employed to analyze the applicability of different containment tests to specified power plant. The test dataoriginating fromHDR ISP-16 and HDR ISP-23can represent the pressure transient process, results of coupling phenomena such as mass and energy release at the break, condensation near the containment shell and internals, within the HPR1000 containment in case of LBLOCA or MSLB. The distortion is either within the acceptable range or conservative for design limits of containment pressure, so that the small-scale containment test data could be suitable for verification and validation of the HPR1000 containment thermal hydraulic response analysis code. © 2025 Xi'an Jiaotong University

关键词： Loss of coolant accidents

来源：评论

学校读者我要写书评

暂无评论

Energy-Consumption Optimization Control for Lunar Rover's Travel with Torque-Distribution-strategy in Rear Wheels

Energy-Consumption Optimization Control for Lunar Rover's Tr...

引用

IEEE International Conference on Control Science and systems Engineering (CCSSE)

作者： Delun Li Jianfei Cao Yiliang Chen Zongwu Xie State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China Beijing Key Laboratory of Intelligent Space Robotic Systems Technology and Applications Beijing Institute of Spacecraft System Engineering Beijing China

ISBN: (数字)9798331517199

ISBN: (纸本)9798331517205

In anticipation of future extensive lunar surface operations, lunar rovers are required to advance towards higher speeds and improved energy conservation. When traveling at high speeds on the lunar surface, the vehicle's energy expenditure is greatly amplified by the influence of the terrain, particularly in conditions where driving and steering are coupled. This paper proposes an energy-saving control strategy for lunar rovers that employs dynamic rear-axle torque distribution, with the goal of optimizing transient energy consumption during travel. To tackle the challenge of non-differentiable functions within the optimization objectives, we suggest using a zeroth-order gradient optimization method for resolution, dynamically constraining the range of control parameters to fulfill the dynamic torque distribution objectives as needed for the task. The energy-saving control effectiveness of the algorithm has been confirmed through simulation, demonstrating a minimum energy-saving ratio of at least 4%, which increases to over 11% as the speed level rises, offering a valuable technical solution for the energy optimization of lunar rovers.

关键词： Space vehicles Energy consumption Torque Distribution strategy Moon Wheels Optimization methods systems engineering and theory Vehicle dynamics Transient analysis

来源：评论

学校读者我要写书评

暂无评论

Design and Experimental Evaluation of WLR-III

Design and Experimental Evaluation of WLR-III

引用

IEEE International Conference on robotics and Biomimetics

作者： Xu Li Yili Fu State Key Laboratory of Robotics and System Harbin Institute of Technology and State Key Laboratory of Fluid Power and Mechatronic Systems Zhejiang University Intelligent Robot Research Center Zhejiang Laboratory and State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China

This paper introduces the design and experimental evaluation of WLR-III, which stands for the third-generation hydraulic wheel-legged robot. WLR-III is expected to be applied to disaster scenarios where the mobility, adaptability and manipulation capability are required. Based on the development of the previous two generations of wheel-legged robots, this work continuously optimizes the design to achieve higher mobility and stronger adaptability by reducing weight & inertia. The hydraulic power transmission system adopts a hose-less design method to ensure the robustness of the system. What's more prominent is that the successful development of hydraulic power unit (HPU) enables WLR-III to realize hydraulic power autonomy. In addition, to accomplish all kinds of operational tasks in the rescue scene, the electro-hydraulic hybrid drives anthropomorphic arms with heavy load grippers were developed. Finally, the effectiveness and reliability of design optimization have been evaluated through a series of experiments, including grassland movement, load bearing, obstacle-stepping and tool-operating. To the authors' best knowledge, this is the first time that a hydraulic powered autonomous wheel-legged humanoid robot with the ability to operate simple tools has been developed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural-Network-Driven Reward Prediction as a Heuristic: Advancing Q-Learning for Mobile Robot Path Planning

arXiv

引用

arXiv 2024年

作者： Ji, Yiming Yun, Kaijie Liu, Yang Xie, Zongwu Liu, Hong State Key Laboratory of Robotics and Systems Harbin Institute of Technology China

Q-learning is a widely used reinforcement learning technique for solving path planning problems. It primarily involves the interaction between an agent and its environment, enabling the agent to learn an optimal strategy that maximizes cumulative rewards. Although many studies have reported the effectiveness of Q-learning, it still faces slow convergence issues in practical applications. To address this issue, we propose the NDR-QL method, which utilizes neural network outputs as heuristic information to accelerate the convergence process of Q-learning. Specifically, we improved the dual-output neural network model by introducing a start-end channel separation mechanism and enhancing the feature fusion process. After training, the proposed NDR model can output a narrowly focused optimal probability distribution, referred to as the guideline, and a broadly distributed suboptimal distribution, referred to as the region. Subsequently, based on the guideline prediction, we calculate the continuous reward function for the Q-learning method, and based on the region prediction, we initialize the Q-table with a bias. We conducted training, validation, and path planning simulation experiments on public datasets. The results indicate that the NDR model outperforms previous methods by up to 5% in prediction accuracy. Furthermore, the proposed NDR-QL method improves the convergence speed of the baseline Q-learning method by 90% and also surpasses the previously improved Q-learning methods in path quality metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Magnetic-Driven Tubular Micromotors with Bases for Precise Positioning and Cargo Carrying

引用

Nanomanufacturing and Metrology 2025年第1期8卷 1-7页

作者： Chen, Peiqi Jia, Ying Wang, Shutong Ding, Shaobo Zhou, Dekai Feng, Yiwen State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China Sinopec Key Laboratory of Marine Oil & Gas Reservoir Production Beijing China Key Laboratory for Micro/Nano Technology and System of Liaoning Province Dalian University of Technology Dalian China Liaoning Huanghai Laboratory Dalian China

Micro/nanomotors present considerable potential in various fields, such as medical treatment, environmental remediation, and cell engineering. However, their restricted lifetime and issues in navigation control hinder their applications in cases requiring precise positioning without chemical fuels. Thus, we propose a tubular micromotor driven by external magnetic fields, enabling it to swim in water with accurate transport capabilities. The presented tubular micromotor incorporates a single-sided base, which increases the contact area to enable cargo delivery in liquid environments. The micromotor exhibits varied movement behaviors by applying different magnetic fields, and frequency modulation allows for control over movement velocity. Template-assisted electrochemical deposition is employed to achieve large-scale fabrication, which enables the construction of Ni–Au tubular micromotors with a single-sided base. In addition, the micromotor can trace a predefined path, which demonstrates its precise positioning ability. The cargo transport capability of the micromotor is further validated using polystyrene globules as cargo. This fuel-free tubular micromotor, which is driven by magnetic fields, provides a promising approach for precise cargo delivery. Its broad feasibility makes it suitable for various biomedical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

NEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splatting

arXiv

引用

arXiv 2024年

作者： Ji, Yiming Liu, Yang Xie, Guanghu Ma, Boyu Xie, Zongwu Liu, Hong State Key Laboratory of Robotics and Systems Harbin Institute of Technology China

We propose NEDS-SLAM, a dense semantic SLAM system based on 3D Gaussian representation, that enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in real-time. In the system, we propose a Spatially Consistent Feature Fusion model to reduce the effect of erroneous estimates from pre-trained segmentation head on semantic reconstruction, achieving robust 3D semantic Gaussian mapping. Additionally, we employ a lightweight encoder-decoder to compress the high-dimensional semantic features into a compact 3D Gaussian representation, mitigating the burden of excessive memory consumption. Furthermore, we leverage the advantage of 3D Gaussian splatting, which enables efficient and differentiable novel view rendering, and propose a Virtual Camera View Pruning method to eliminate outlier gaussians, thereby effectively enhancing the quality of scene representations. Our NEDS-SLAM method demonstrates competitive performance over existing dense semantic SLAM methods in terms of mapping and tracking accuracy on Replica and ScanNet datasets, while also showing excellent capabilities in 3D dense semantic mapping. Index Terms—3D Gaussian Splatting;Dense Semantic Mapping;Neural SLAM;3D Reconstruction. Copyright © 2024, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Design of Bionic Manta Ray Driven by SMA 7

Design of Bionic Manta Ray Driven by SMA

引用

7th International Conference on Control and robotics Engineering, ICCRE 2022

作者： Liu, Yiwei Chen, Zhiyuan Chen, Changjiang Wang, Tao Tian, Guoping Ji, Shihang State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin China Shanghai Aerospace Equipment Manufacturing General Factory Co. Ltd Shanghai China

ISBN: (纸本)9781665468404

Taking manta ray as bionic object, a kind of bionic robot fish was designed, which was propelled by pectoral fin and driven by SMA (shape memory alloy) wire. Firstly, the model and driving structure were designed according to the appearance and motion mechanism of manta ray. Then, the mechanical model of the designed bionic pectoral fin was established, and the relationship between the pectoral fin swing angle and the current was obtained by combining with the thermodynamic model of SMA. Then, the motion law was determined by theoretical analysis, and the control system was designed. Finally, the prototype was made, and the experiments of pectoral fin swing and bionic manta ray swimming were carried out respectively. © 2022 IEEE.

关键词： Bionics

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：