检索结果-内蒙古大学图书馆

Human Following Robot Based on Object Detection for Aerospace Application

学校读者我要写书评

暂无评论

Human Following Robot Based on Object Detection for Aerospac...

Aerospace Electrical engineering and Informatics (ICAAEEI), International Conference of Adisutjipto on

作者： Arwin Datumava Wahvudi Sumari Ahnaf Bagus Aryandika Ndaru Atmi Purnami Denny Dermawan Ika Noer Syamsiana Department of Electrical Engineering Cognitive Artificial Intelligence Research Group State Polytechnic of Malang Malang Indonesia Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Navigation Instrumentation Control Automation and Robotics System Research Group Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Digital System Microprocessor Microcontroller and Programmable Logic Devices Research Group Electrical Engineering Study Program Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia

ISBN: (数字)9798331507930

ISBN: (纸本)9798331507947

In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraft technicians by bringing maintenance tool kits to aircraft shelters. Rewang's movement is based on a camera as a vision sensor following the movement of human entities. Image input is processed by YOLO v3-Tiny through the determination of the bounding box, the calculation of Euclidean Distance, and the determination of the pixel value of the camera as the basis of Rewang's movement which is regulated by an L298N driver motor that controls two Direct Current (DC) motors for the left and right wheels. The test results show that Rewang can move at an average speed of 0.18 m/s at 2 m with a travel time of 11 seconds with a light intensity of more than 250 lux. The minimum and maximum distance of object detection is as far as 120 cm and 400 cm, with an object detection accuracy of 95.8%. Rewang allows the HFR to have a larger carrying capacity to bring more complete aircraft maintenance tools and is prospective for other aerospace and general applications.

关键词： YOLO Tensors Accuracy Prototypes Wheels Cameras Hardware Maintenance Aircraft Aerospace industry

A Space Crawling Robotic Bio-Paw (Scrbp) Enabled by Triboelectric Sensors for Surface Identification

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Hou, Xuyan Zhang, Li Gao, Guowei Liu, Yuhui Na, Zhonglai Xu, QingZhang Ding, Tianxiang Li, Long Chen, Tao Research Center of Aerospace Mechanism and Control School of Mechatronics Engineering Harbin Institute of Technology Harbin150080 China Department of MECHANICAL ENGINEERING FACULTY OF ENGINEERING Hong Kong Polytechnic University Hong Kong Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China Jiangsu Provincial Key Laboratory of Advanced Robotics School of Mechanical and Electric Engineering Soochow University Suzhou215123 China

With the rapid development of space crawling robotics technology, tactile perception, a significant source for the robot to sense the external environment, has become the preferred solution to gather information in space. Sensors embedded in the robotic end-effector unit can collect and encode the large tactile data, allowing the robot to feel and perceive the real surroundings. Therefore, a space crawling robotic bio-paw (SCRBP) inspired by a cat paw, which performs as a compliant device and can flat the impulse force during the robot’s contact process to the target surface, is proposed in this paper. Meanwhile, a touch-sensing system embedded on SCRBP with self-powered sensors based on the triboelectric nanogenerator (TENG) technology is proposed which can provide the multi-dimensional sensation information in real time. By combining with machine learning (ML), the sensory system can be used for surface identification from the footfall process to the robot’s controller hub. In conclusion, SCRBP device proposed in this paper has obvious advantages in surface information acquisition, space adaptability, power consumption, cost, reliable signal and minimized data. Accordingly, SCRBP system shows fabulous potential in space robotics. © 2022, The Authors. All rights reserved.

关键词： End effectors

Fully Decentralized Design of Initialization-free Distributed Network Size Estimation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lee, Donggil Kim, Taekyoo Lee, Seungjoon Shim, Hyungbo Center for Intelligent and Interactive Robotics Korea Institute of Science and Technology Seoul02792 Korea Republic of The Train Control and Communication Team Korea Railroad Research Institute Uiwang16105 Korea Republic of NAVER Labs Seongnam13161 Korea Republic of ASRI Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of

In this paper, we propose a distributed scheme for estimating the network size, which refers to the total number of agents in a network. By leveraging a synchronization technique for multi-agent systems, we devise an agent dynamics that ensures convergence to an equilibrium point located near the network size regardless of its initial condition. Our approach is based on an assumption that each agent has a unique identifier, and an estimation algorithm for obtaining the largest identifier value. By adopting this approach, we successfully implement the agent dynamics in a fully decentralized manner, ensuring accurate network size estimation even when some agents join or leave the network. © 2024, CC BY-NC-ND.

关键词： Multi agent systems

3D Scene Flow Estimation on Pseudo-LiDAR: Bridging the Gap on Estimating Point Motion

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Chaokang Wang, Guangming Miao, Yanzi Wang, Hesheng Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China

3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for estimating scene flow from images have limitations, which split the holistic nature of 3D scene flow by estimating optical flow and disparity separately. Learning 3D scene flow from point clouds also faces the difficulties of the gap between synthesized and real data and the sparsity of LiDAR point clouds. In this paper, the generated dense depth map is utilized to obtain explicit 3D coordinates, which achieves direct learning of 3D scene flow from 2D images. The stability of the predicted scene flow is improved by introducing the dense nature of 2D pixels into the 3D space. Outliers in the generated 3D point cloud are removed by statistical methods to weaken the impact of noisy points on the 3D scene flow estimation task. Disparity consistency loss is proposed to achieve more effective unsupervised learning of 3D scene flow. The proposed method of self-supervised learning of 3D scene flow on real-world images is compared with a variety of methods for learning on the synthesized dataset and learning on LiDAR point clouds. The comparisons of multiple scene flow metrics are shown to demonstrate the effectiveness and superiority of introducing pseudo-LiDAR point cloud to scene flow estimation. © 2022, CC BY.

关键词： Three dimensional computer graphics

Unsupervised Learning of 3D Scene Flow with 3D Odometry Assistance

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Guangming Feng, Zhiheng Jiang, Chaokang Wang, Hesheng Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai200240 China Engineering Research Center of Intelligent Control for Underground Space Ministry of Education School of Information and Control Engineering Advanced Robotics Research Center China University of Mining and Technology Xuzhou221116 China

Scene flow represents the 3D motion of each point in the scene, which explicitly describes the distance and the direction of each point’s movement. Scene flow estimation is used in various applications such as autonomous driving fields, activity recognition, and virtual reality fields. As it is challenging to annotate scene flow with ground truth for real-world data, this leaves no real-world dataset available to provide a large amount of data with ground truth for scene flow estimation. Therefore, many works use synthesized data to pre-train their network and real-world LiDAR data to finetune. Unlike the previous unsupervised learning of scene flow in point clouds, we propose to use odometry information to assist the unsupervised learning of scene flow and use real-world LiDAR data to train our network. Supervised odometry provides more accurate shared cost volume for scene flow. In addition, the proposed network has mask-weighted warp layers to get a more accurate predicted point cloud. The warp operation means applying an estimated pose transformation or scene flow to a source point cloud to obtain a predicted point cloud and is the key to refining scene flow from coarse to fine. When performing warp operations, the points in different states use different weights for the pose transformation and scene flow transformation. We classify the states of points as static, dynamic, and occluded, where the static masks are used to divide static and dynamic points, and the occlusion masks are used to divide occluded points. The mask-weighted warp layer indicates that static masks and occlusion masks are used as weights when performing warp operations. Our designs are proved to be effective in ablation experiments. The experiment results show the promising prospect of an odometry-assisted unsupervised learning method for 3D scene flow in real-world data. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

High throughput event filtering: The interpolation-based DIF algorithm hardware architecture

学校读者我要写书评

暂无评论

Microprocessors and Microsystems 2025年

作者： Marcin Kowalczyk Tomasz Kryjak Embedded Vision Systems Group Department of Automatic Control and Robotics Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering AGH University of Krakow Poland

In recent years, there has been rapid development in the field of event vision. It manifests itself both on the technical side, as better and better event sensors are available, and on the algorithmic side, as more and more applications of this technology are proposed and scientific papers are published. However, the data stream from these sensors typically contains a significant amount of noise, which varies depending on factors such as the degree of illumination in the observed scene or the temperature of the sensor. We propose a hardware architecture of the Distance-based Interpolation with Frequency Weights(DIF) filter and implement it on an FPGA chip. To evaluate the algorithm and compare it with other solutions, we have prepared a new high-resolution event dataset, which we are also releasing to the community. Our architecture achieved a throughput of 403.39 million events per second (MEPS) for a sensor resolution of 1280 × 720 and 428.45 MEPS for a resolution of 640 × 480. The averagevalues of the Area Under the Receiver Operating Characteristic (AUROC) index ranged from 0.844 to 0.999, depending on the dataset, which is comparable to the state-of-the-art filtering solutions, but with much higher throughput and better operation over a wide range of noise levels.

关键词： Dataset Denoising DVS FPGA High-throughput

Self-supervised Multi-frame Monocular Depth Estimation with Pseudo-LiDAR Pose Enhancement

学校读者我要写书评

暂无评论

Self-supervised Multi-frame Monocular Depth Estimation with ...

IEEE International Conference on robotics and Automation (ICRA)

作者： Wenhua Wu Guangming Wang Jiquan Zhong Hesheng Wang Zhe Liu MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Insititute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Depth estimation is one of the most important tasks in scene understanding. In the existing joint self-supervised learning approaches of depth-pose estimation, depth estimation and pose estimation networks are independent of each other. They only use the adjacent image frames for pose estimation and lack the use of the estimated geometric information. To enhance the depth-pose association, we propose a monocular multi-frame unsupervised depth estimation framework, named PLPE-Depth. There are a depth estimation network and two pose estimation networks with image input and pseudo-LiDAR input. The main idea of our approach is to use the pseudo-LiDAR reconstructed from the depth map to estimate the pose of adjacent frames. We propose depth re-estimation with a better pose between the image pose and the pseudo-LiDAR pose to improve the accuracy of estimation. Besides, we improve the reconstruction loss and design a pseudo-LiDAR pose enhancement loss to facilitate the joint learning. Our approach enhances the use of the estimated depth information and strengthens the coupling between depth estimation and pose estimation. Experiments on the KITTI dataset show that our depth estimation achieves state-of-the-art performance at low resolution. Our source codes will be released on https://***/IRMVLabIPLPE-Depth.

关键词：

A social power game for the concatenated Friedkin-Johnsen model

学校读者我要写书评

暂无评论

A social power game for the concatenated Friedkin-Johnsen mo...

IEEE Conference on Decision and control

作者： Lingfei Wang Guanpu Chen Yiguang Hong Guodong Shi Claudio Altafini Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences and also with the University of Chinese Academy of Sciences Beijing China JD Explore Academy Beijing China Department of Control Science and Engineering Tongji University Shanghai China Australian Center for Field Robotics School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney NSW Sydney Department of Electrical Engineering Division of Automatic Control Linköping University Linköping Sweden

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

If a concatenated Friedkin-Johnsen model is used to describe the evolution of the opinions of stubborn agents in a sequence of discussion events, then the social power achieved by the agents at the end of the discussions depends from the stubbornness coefficients adopted by the agents through the sequence of events. In this paper we assume that the agents are free to choose their stubbornness profiles, and ask ourselves what strategy should an agent follow in order to maximize its social power. Formulating the problem as a strategic game, we show that choosing the highest possible values of stubbornness in the early discussions leads to the highest possible social power.

关键词： Games

Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Yu Zhang, Yuexin Li, Kunming Qiao, Yongliang Worrall, Stewart Li, You-Fu Kong, He Shenzhen518055 China Department of Mechanical Engineering City University of Hong Kong Hong Kong School of Automation Guangdong Polytechnic Normal University Guangzhou510665 China Australian Centre for Field Robotics The University of Sydney NSW2006 Australia Australian Institute for Machine Learning The University of Adelaide SA5005 Australia Shenzhen Key Laboratory of Control Theory and Intelligent Systems SUSTech Shenzhen518055 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities SUSTech Shenzhen518055 China

Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles. Accurately forecasting crowd trajectories is challenging due to the uncertain nature of human motions in different environments. For training, recent deep learning-based prediction approaches mainly utilize information like trajectory history and interactions between pedestrians, among others. This can limit the prediction performance across various scenarios since the discrepancies between training datasets have not been properly incorporated. To overcome this limitation, this paper proposes a graph transformer structure to improve prediction performance, capturing the differences between the various sites and scenarios contained in the datasets. In particular, a self-attention mechanism and a domain adaption module have been designed to improve the generalization ability of the model. Moreover, an additional metric considering crossdataset sequences is introduced for training and performance evaluation purposes. The proposed framework is validated and compared against existing methods using popular public datasets, i.e., ETH and UCY. Experimental results demonstrate the improved performance of our proposed scheme. © 2024, CC BY.

关键词： Trajectories