检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Wang, Han Wang, Gongcheng Zhu, Hongbiao Du, Chengjin Bai, Hua Ding, Pengchao Xu, Wenda Du, Zhijiang Wang, Weidong The State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150080 China Istituto Italiano di Tecnologia The BioRobotics Institute Scuola Superiore Sant’Anna Genova16163 Italy

The application of autonomous navigation in mobile robots has seen notable success in indoor, structured 2D environments. However, applying this technology to outdoor, 3D unstructured environments — especially on uneven terrains, presents significant challenges. To address this, we propose a navigation framework for uneven terrain based on continuous traversability analysis. Our methodology unfolds in three stages: First, Bayesian generalized kernel inference is employed to estimate attributes of the unobserved point cloud, enabling the computation of continuous terrain traversability values by using dispersed point cloud data. Second, an improved A* (TRA-A*) algorithm is proposed for global path determination. In the final stage, nonlinear model predictive control (NMPC) is utilized for path following. This involves integrating the traversable exponents and uncertainty into the cost function, resulting in a safety-focused motion planning algorithm that encourages the navigation stability of the robot. The effectiveness of this method was verified through simulation and actual scene experiments. This algorithm improves the robot's navigation success rate by 8% while sacrificing a small amount of 9.83% of the path length in the actual environment, preventing the robot from tipping over or getting stuck in rough terrain, and improving the stationarity of the robot during driving. It reduces the cost of the terrain the robot travels on by 42.6%, reduces the robot's longitudinal acceleration fluctuation and lateral angular velocity fluctuation by 28.52% and 28.9% respectively, and improves the robot's driving stability. © 2024, The Authors. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Matching of Humanoid-Eye Binocular Images Based on Susan-Sift Algorithm

SSRN

引用

SSRN 2023年

作者： Xia, Xiaohua Xiang, Haoming Cao, Yusong Ge, Zhaokai Jiang, Zainan Key Laboratory of Road Construction Technology and Equipment MOE Chang’an University Xi’an710064 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

Imitating the visual characteristics of human eyes is one of the important tasks of digital image processing and computer vision. Feature correspondence of humanoid-eye binocular images is a fundamental step. However, in some scenes, due to a lack of edge features and mismatching problems, the performance of humanoid-eye binocular images in feature matching is greatly limited. To address the aforementioned challenges, a method of feature extraction and matching based on SUSAN-SIFT algorithm is proposed in this paper. The SUSAN detector is utilized in the feature detection stage for its outstanding edge feature extraction capability like human eyes. Then we build a multi-scale SIFT descriptor, to provide the neighborhood information at different resolutions for each feature and guide feature points to generate the corresponding pairs. Compared with state-of-the-art algorithms, the method can improve matching accuracy while retaining more edge features, and its resulting feature pairs are more evenly distributed. © 2023, The Authors. All rights reserved.

关键词： Binoculars

来源：评论

学校读者我要写书评

暂无评论

YOWO-Plus: An Incremental Improvement

arXiv

引用

arXiv 2022年

作者： Yang, Jianhua State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

In this technical report, we would like to introduce our updates to YOWO, a real-time method for spatio-temporal action detection. We make a bunch of little design changes to make it better. For network structure, we use the same ones of official implemented YOWO, including 3D-ResNext-101 and YOLOv2, but we use a better pretrained weight of our reimplemented YOLOv2, which is better than the official YOLOv2. We also optimize the label assignment used in YOWO. To accurately detection action instances, we deploy GIoU loss for box regression. After our incremental improvement, YOWO achieves 84.9% frame mAP and 50.5% video mAP on the UCF101-24, significantly higher than the official YOWO. On the AVA, our optimized YOWO achieves 20.6% frame mAP with 16 frames, also exceeding the official YOWO. With 32 frames, our YOWO achieves 21.6 frame mAP with 25 FPS on an RTX 3090 GPU. We name the optimized YOWO as YOWO-Plus. Moreover, we replace the 3D-ResNext-101 with the efficient 3D-ShuffleNet-v2 to design a lightweight action detector, YOWO-Nano. YOWO-Nano achieves 81.0 % frame mAP and 49.7% video frame mAP with over 90 FPS on the UCF101-24. It also achieves 18.4 % frame mAP with about 90 FPS on the AVA. As far as we know, YOWO-Nano is the fastest state-of-the-art action detector. Our code is available on https://***/yjh0410/PyTorch_YOWO. © 2022, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prototype Design and Efficiency Analysis of a Novel Robot Drive Based on 3K-H-V Topology

arXiv

引用

arXiv 2022年

作者： Qi, Le Yang, Dapeng Cao, Baoshi Li, Zhiqi Gu, Yikun Xie, Zongwu Liu, Hong The State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150080 China

Robot actuators directly affect the performance of robots, and robot drives directly affect the performance of robot actuators. With the development of robotics, robots have put higher requirements on robot drives, such as high stiffness, high accuracy, high loading, high efficiency, low backlash, compact size, and hollow structure. In order to meet the demand development of robot actuators, this research base proposes a new robot drive based on 3K-H-V topology using involute and cycloidal gear shapes, planetary cycloidal drive, from the perspective of drive topology and through the design idea of decoupling. In this study, the reduction ratio and the efficiency model of the 3K-H-V topology were analyzed, and a prototype planetary cycloidal actuator was designed. The feasibility of the drive is initially verified by experimentally concluding that the PCA has a hollow structure, compact size, and high torque density (69 Nm/kg). Copyright © 2022, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Simulation study of a spider-like robot based on leg reorganization

Simulation study of a spider-like robot based on leg reorgan...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Wang, Shu Qi Fan, Ji Zhuang Zhang, Kuan Zhang, Wei Liu, Gang Feng Zhao, Jie Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China Harbin University of Science and Technology College of Mechanical and Power Engineering Harbin China

ISBN: (纸本)9781665436786

This paper presents a four-legged bionic robot based on leg reorganization with the hunter spider as the bionic research object. By studying the biological structure of the hunter spider, its movement mode, and the characteristics of limb movement during the conversion process is analyzed and the principle of wheel and foot conversion of the robot is obtained. The three-dimensional model of the bionic robot is designed, and the overall assembly of the bionic structure model is completed. The rationality of the design of the bionic structure is initially verified by the leg reorganization. The virtual prototype is built by adding constraints to realize the bionic motion simulation, including in-situ rotary motion, foot-wheel conversion motion, wheel motion, wheel-foot conversion motion, foot motion, which provides a theoretical basis for the development of the physical prototype and the selection of hardware. © 2021 IEEE.

关键词： Wheels

来源：评论

学校读者我要写书评

暂无评论

A bionic approach for the mechanical and electrical decoupling of an MEMS capacitive sensor in ultralow force measurement

引用

Frontiers of Mechanical Engineering 2023年第2期18卷 297-317页

作者： Wendi GAO Bian TIAN Cunlang LIU Yingbiao MI Chen JIA Libo ZHAO Tao LIU Nan ZHU Ping YANG Qijing LIN Zhuangde JIANG Dong SUN State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement TechnologiesOverseas Expertise Introduction Center for Micro/Nano Manufacturing and Nano Measurement Technologies Discipline InnovationXi’an Jiaotong University(Yantai)Research Institute for Intelligent Sensing Technology and SystemSchool of Mechanical EngineeringXi’an Jiaotong UniversityXi’an 710049China Shandong Laboratory of Yantai Advanced Materials and Green Manufacturing Yantai 265599China State Key Laboratory of Robotics and Systems(HIT) Harbin 150006China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of TechnologyBeijing 100081China Department of Biomedical Engineering City University of Hong KongHong KongChina

Capacitive sensors are efficient tools for biophysical force measurement,which is essential for the exploration of cellular ***,attention has been rarely given on the influences of external mechanical and internal electrical interferences on capacitive *** this work,a bionic swallow structure design norm was developed for mechanical decoupling,and the influences of structural parameters on mechanical behavior were fully analyzed and optimized.A bionic feather comb distribution strategy and a portable readout circuit were proposed for eliminating electrostatic *** instability was evaluated,and electrostatic decoupling performance was verified on the basis of a novel measurement method utilizing four complementary comb arrays and applicationspecific integrated circuit *** electrostatic pulling experiment showed that the bionic swallow structure hardly moved by 0.770 nm,and the measurement error was less than 0.009% for the area-variant sensor and 1.118% for the gap-variant sensor,which can be easily compensated in *** proposed sensor also exhibited high resistance against electrostatic rotation,and the resulting measurement error dropped below 0.751%.The rotation interferences were less than 0.330 nm and(1.829×10^(-7))°,which were 35 times smaller than those of the traditional differential *** on the proposed bionic decoupling method,the fabricated sensor exhibited overwhelming capacitive sensitivity values of 7.078 and 1.473 pF/μm for gap-variant and area-variant devices,respectively,which were the highest among the current *** immunity to mechanical disturbances was maintained simultaneously,i.e.,less than 0.369% and 0.058% of the sensor outputs for the gap-variant and area-variant devices,respectively,indicating its great performance improvements over existing devices and feasibility in ultralow biomedical force measurement.

关键词： micro-electro-mechanical system capacitive sensor bionics operation instability mechanical and electrical decoupling biomedical force measurement

来源：评论

学校读者我要写书评

暂无评论

DeepMatcher: A Deep Transformer-based Network for Robust and Accurate Local Feature Matching

arXiv

引用

arXiv 2023年

作者： Xie, Tao Dai, Kun Wang, Ke Li, Ruifeng Zhao, Lijun State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China SenseTime Group Inc. Beijing100080 China

Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes. In this work, we propose DeepMatcher, a deep Transformer-based network built upon our investigation of local feature matching in detector-free methods. The key insight is that local feature matcher with deep layers can capture more human-intuitive and simpler-to-match features. Based on this, we propose a Slimming Transformer (SlimFormer) dedicated for DeepMatcher, which leverages vector-based attention to model relevance among all keypoints and achieves long-range context aggregation in an efficient and effective manner. A relative position encoding is applied to each SlimFormer so as to explicitly disclose relative distance information, further improving the representation of keypoints. A layer-scale strategy is also employed in each SlimFormer to enable the network to assimilate message exchange from the residual block adaptively, thus allowing it to simulate the human behaviour that humans can acquire different matching cues each time they scan an image pair. To facilitate a better adaption of the SlimFormer, we introduce a Feature Transition Module (FTM) to ensure a smooth transition in feature scopes with different receptive fields. By interleaving the self- and cross-SlimFormer multiple times, DeepMatcher can easily establish pixel-wise dense matches at coarse level. Finally, we perceive the match refinement as a combination of classification and regression problems and design Fine Matches Module to predict confidence and offset concurrently, thereby generating robust and accurate matches. Experimentally, we show that DeepMatcher significantly outperforms the state-of-the-art methods on several benchmarks, demonstrating the superior matching capability of DeepMatcher. The code is available at https://***/XT1997/DeepMatcher. © 2023, CC BY.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Visual Servo Stabilization of Nonholonomic Mobile Robot Based on Epipolar Geometry and 1D Trifocal Tensor

引用

Chinese Journal of Electronics 2023年第4期22卷 729-734页

作者： CAO Zhengcai YIN Longjie FU Yili ZHANG Jie College of Information Science and Technology Beijing University of Chemical Technology Beijing China The State Key Laboratory of Robotics and Systems Harbin Institute of Technology Harbin China

In this paper, a visual servo stabilization approach consisting in a dynamic switching control law for a nonholonomic mobile robot is presented, which applies the epipolar geometry and the 1D trifocal tensor to drive the robot to a desired configuration. The whole motion process is divided into three steps. Firstly, an epipole-based control law is designed to make the robot rotate in place until the camera points to the desired position. The 1D trifocal tensor is then used in the second translation step to reach the desired place. Finally, the desired configuration is reached through a pure rotation using the epipolar geometry. The stability of the proposed control system is proved based on linear system control theory and Lyapunov theory. Simulation results are given to illustrate the effectiveness of the proposed controller.

关键词： Geometry Linear systems Visualization Tensors Simulation Switches Control systems

来源：评论

学校读者我要写书评

暂无评论

OAMatcher: An Overlapping Areas-based Network for Accurate Local Feature Matching

arXiv

引用

arXiv 2023年

作者： Dai, Kun Xie, Tao Wang, Ke Jiang, Zhiqiang Li, Ruifeng Zhao, Lijun State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150006 China SenseTime Group Inc. Beijing100080 China

Local feature matching is an essential component in many visual applications. In this work, we propose OAMatcher, a Tranformer-based detector-free method that imitates humans behavior to generate dense and accurate matches. Firstly, OAMatcher predicts overlapping areas to promote effective and clean global context aggregation, with the key insight that humans focus on the overlapping areas instead of the entire images after multiple observations when matching keypoints in image pairs. Technically, we first perform global information integration across all keypoints to imitate the humans behavior of observing the entire images at the beginning of feature matching. Then, we propose Overlapping Areas Prediction Module (OAPM) to capture the keypoints in co-visible regions and conduct feature enhancement among them to simulate that humans transit the focus regions from the entire images to overlapping regions, hence realizeing effective information exchange without the interference coming from the keypoints in non-overlapping areas. Besides, since humans tend to leverage probability to determine whether the match labels are correct or not, we propose a Match Labels Weight Strategy (MLWS) to generate the coefficients used to appraise the reliability of the ground-truth match labels, while alleviating the influence of measurement noise coming from the data. Moreover, we integrate depth-wise convolution into Tranformer encoder layers to ensure OAMatcher extracts local and global feature representation concurrently. Comprehensive experiments demonstrate that OAMatcher outperforms the state-of-the-art methods on several benchmarks, while exhibiting excellent robustness to extreme appearance variants. The source code is available at https://***/DK-HU/OAMatcher. © 2023, CC BY.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-sensor Fusion Localization of Wheel-Legged Robots in Dynamic Scenarios

Research on Multi-sensor Fusion Localization of Wheel-Legged...

引用

Automation, Control and Robots (ICACR), International Conference on

作者： Xu Li Yili Fu Zuolun Cheng State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin 150001 China Intelligent Robot Research Center Zhejiang Laboratory Hangzhou 311100 China

With the rapid development of human beings in motion control and localization perception, intelligent mobile robots are widely used in various scenarios, such as industrial production, medical care, logistics and distribution. Among them, wheel-legged robots have both the high mobility of wheeled robots and the high adaptability of legged robots, which can not only move fast on platform terrain, but also adapt to rugged and complex ground with the multiple degrees of freedom of their legs. Wheel-legged robots face the following main problems in high-precision robust localization in multiple scenarios: there are a lot of dynamic factors in daily indoor and outdoor scenarios, such as vehicles, pedestrians, etc., which require specific processing of dynamic environment in the visual front-end part to improve the effect of visual factor constraints; as ground mobile robots, the localization framework of visual inertial fusion (VIO) will show scale degeneration phenomenon, resulting in long-distance localization accuracy decline. In addition, as a two wheeled inverted pendulum robot, the ground constraint form will undergo corresponding changes. Aiming at the above problems, this paper takes the hydraulic-driven wheel-legged robot as the object and proposes a multi-sensor fusion localization method in dynamic scenarios.

关键词：

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：