检索结果-内蒙古大学图书馆

LiDAR-MIMO: Efficient Uncertainty Estimation for LiDAR-based 3D Object Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pitropov, Matthew Huang, Chengjie Abdelzad, Vahdat Czarnecki, Krzysztof Waslander, Steven Department of Electrical and Computer Engineering University of Waterloo Canada David R. Cheriton School of Computer Science University of Waterloo Canada University of Toronto Robotics Institute Canada

The estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance. However, the deployment of current uncertainty estimation methods in 3D object detection remains challenging due to timing and computational constraints. To tackle this issue, we propose LiDAR-MIMO, an adaptation of the multi-input multi-output (MIMO) uncertainty estimation method to the LiDAR-based 3D object detection task. Our method modifies the original MIMO by performing multi-input at the feature level to ensure the detection, uncertainty estimation, and runtime performance benefits are retained despite the limited capacity of the underlying detector and the large computational costs of point cloud processing. We compare LiDAR-MIMO with MC dropout and ensembles as baselines and show comparable uncertainty estimation results with only a small number of output heads. Further, LiDAR-MIMO can be configured to be twice as fast as MC dropout and ensembles, while achieving higher mAP than MC dropout and approaching that of ensembles. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

Learner Action Patterns in the Problem-Solving Process Related to program Code Composition Based on Tracking System Activities 7

学校读者我要写书评

暂无评论

Learner Action Patterns in the Problem-Solving Process Relat...

7th International Conference on Informatics and Computing, ICIC 2022

作者： Syahidi, Aulia Akhrian Supianto, Ahmad Afif Hirashima, Tsukasa Watanobe, Yutaka Politeknik Negeri Banjarmasin Smart City Information System Applied Undergraduate Program Banjarmasin City Indonesia Research Center for Data and Information Sciences Bandung City Indonesia Graduate School of Advanced Science and Engineering Hiroshima University Kagamiyama Learning Engineering Laboratory Higashihiroshima Japan University of Aizu Division of Information Systems Department of Computer Science and Engineering Fukushima AizuWakamatsu Japan

ISBN: (纸本)9798350345711

Learning activities are an indicator of the learner's desire to learn during the learning process. The pattern of learner action is related to learning activities. In this case, in extracting the learning process, it is necessary to collect a lot of data through analysis of the learning process. The purpose of this study is to recommend and report the performance of an activity tracking system equipped with visual artifacts as an educational data mining approach to analyze action patterns when learners complete the arrangement of program code lines in each programming problem. In this study, data were taken from activity recordings when learners used interactive learning media for a basic programming subject called TOLSYASUPI-EduMed which had problem-solving learning models embedded in their interactions. Learning Analytics is used as a method of this research and data relationships from learner actions during the learning process using the 'if-then' rule. Log data is used for recording and detecting activities carried out by learners. We confirm that the results of the study are based on the findings of the data relationship that if the lines of program code are too long (more than five lines) then almost all learners experience a bottleneck condition. The completion time of each question and the number of iterations in completing the program code lines for each question have also been recorded and have a pattern of connection between the data. The information that has been obtained is then forwarded to teachers or stakeholders as key information to make appropriate feedback to learners based on the results as a means of analyzing and evaluating the programming learning process. © 2022 IEEE.

关键词： Data mining

3D Printed 6-Axis Collaborative Arm Robot Using Force Limiting Feature for Service Robot 3

学校读者我要写书评

暂无评论

3D Printed 6-Axis Collaborative Arm Robot Using Force Limiti...

3rd International Conference on Eco engineering Development, ICEED 2019

作者： Saerang, Raymond Wiliem, David Tinggogoy, Feraldy Carles, Deddi Dani, M. Suwandi, Agri Oey, Endra Tan, Sofyan Automotive and Robotics Engineering Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia

Collaborative arm robot is a robot that can work alongside humans. By using force limiting (FL) feature, where the force of the arm robot is limited and controlled, the robot can sense collision and stop its movement when it occurs. The idea is to apply the mentioned concept for service purposes. In this research a 6-axis arm robot with collision detection is developed. The design of the arm robot adopted the design of Universal Robot's UR3 with each joint capable of 360° rotation. The design approach is chosen for its flexibility to work in tight space with a maximum reach of half meter, as it is intended to work closely with human. This initial version robot is not intended to carry heavy load or move at high precision. With a maximum load of one Kg, this arm robot targets numerous applications that help human to do complex repetitive tasks, extend the reach of human operators, and help humans on many daily chores that usually does not involve heavy loads. The whole frame, which also serve as the cover of the robot, was made by 3D printing with multiple materials that fit to the strength and temperature requirement at each part of the robot. In order to detect collision, the arm robot employed smart servos at each joint with the ability to detect overcurrent and overvoltage, which allow the implementation of force limiting (FL) feature that will stop the robot in case of collision. The resulting arm robot managed to lift1 kg load and able stop its movement in the event of collision. Future research to improve the movement precision of the arm robot by adaptive methods is promising. © 2020 Published under licence by IOP Publishing Ltd.

关键词： 3D printers

An Optimal Path Planning Method with Assigned Endpoints in Grid Maps

学校读者我要写书评

暂无评论

An Optimal Path Planning Method with Assigned Endpoints in G...

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Xiaoxiong Wang Zhuo Wang Zhikang Ge Zhihong Man Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Faculty of Science Engineering and Technology Swinburne University of Technology Melbourne Australia

ISBN: (数字)9798350360868

ISBN: (纸本)9798350360875

In this paper, an optimal path planning method with assigned endpoints is developed for complete coverage in grid maps. It is shown that, the complete coverage path can be generated by merging the coverage paths of multiple subregions. Initially, several path planning templates are constructed to minimize repetition in regular regions. Subsequently, the grid map is decomposed into multiple subregions based on the locations of the assigned endpoints. Each region is then traversed with the corresponding template according to the parity of the region. Finally, all paths within the subregions are merged to form a comprehensive coverage path. It is demonstrated that the resulting path exhibits minimal repetition while covering the grid map completely with assigned endpoints. Simulation results are provided to validate the excellent performance of presented path planning method.

关键词： Industrial electronics Simulation Merging Path planning Computational complexity

Evaluating Immersive Teleoperation Interfaces: Coordinating Robot Radiation Monitoring Tasks in Nuclear Facilities

学校读者我要写书评

暂无评论

Evaluating Immersive Teleoperation Interfaces: Coordinating ...

IEEE International Conference on robotics and Automation (ICRA)

作者： Harvey Stedman Basaran Bahadir Kocer Nejra van Zalk Mirko Kovac Vijay M. Pawar Department of Computer Science Autonomous Manufacturing Laboratory University College London London UK Aerial Robotics Laboratory Imperial College London London UK Department of Aerospace Engineering University of Bristol Bristol UK Dyson School of Design Engineering Imperial College London London UK Laboratory of Sustainability Robotics at the Swiss Federal Laboratories for Materials Science and Technology Switzerland

We present a virtual reality (VR) teleoperation interface for a ground-based robot, featuring dense 3D environment reconstruction and a low latency video stream, with which operators can immersively explore remote environments. At the UK Atomic Energy Authority's (UKAEA) Remote Applications in Challenging Environments (RACE) facility, we applied the interface in a user study where trained robotics operators completed simulated nuclear monitoring and decommissioning style tasks to compare VR and traditional teleoperation interface designs. We found that operators in the VR condition took longer to complete the experiment, had reduced collisions, and rated the generated 3D map with higher importance when compared to non-VR operators. Additional physiological data suggested that VR operators had a lower objective cognitive workload during the experiment but also experienced increased physical demand. Overall the presented results show that VR interfaces may benefit work patterns in teleoperation tasks within the nuclear industry, but further work is needed to investigate how such interfaces can be integrated into real world decommissioning workflows.

关键词：

Complementary Information Mutual Learning for Multimodality Medical Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shen, Chuyun Li, Wenhao Chen, Haoqing Wang, Xiaoling Zhu, Fengping Li, Yuxin Wang, Xiangfeng Jin, Bo School of Computer Science and Technology East China Normal University Shanghai200062 China School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518172 China Huashan Hospital Fudan University Shanghai200040 China School of Computer Science and Technology East China Normal University Shanghai AI Laboratory Shanghai200062 China School of Software Engineering Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai200092 China

Radiologists must utilize medical images of multiple modalities for tumor segmentation and diagnosis due to the limitations of medical imaging technology and the diversity of tumor signals. This has led to the development of multimodal learning in medical image segmentation. However, the redundancy among modalities creates challenges for existing subtraction-based joint learning methods, such as misjudging the importance of modalities, ignoring specific modal information, and increasing cognitive load. These thorny issues ultimately decrease segmentation accuracy and increase the risk of overfitting. This paper presents the complementary information mutual learning (CIML) framework, which can mathematically model and address the negative impact of inter-modal redundant information. CIML adopts the idea of addition and removes inter-modal redundant information through inductive bias-driven task decomposition and message passing-based redundancy filtering. CIML first decomposes the multimodal segmentation task into multiple subtasks based on expert prior knowledge, minimizing the information dependence between modalities. Furthermore, CIML introduces a scheme in which each modality can extract information from other modalities additively through message passing. To achieve non-redundancy of extracted information, the redundant filtering is transformed into complementary information learning inspired by the variational information bottleneck. The complementary information learning procedure can be efficiently solved by variational inference and cross-modal spatial attention. Numerical results from the verification task and standard benchmarks indicate that CIML efficiently removes redundant information between modalities, outperforming SOTA methods regarding validation accuracy and segmentation effect. To emphasize, message-passing-based redundancy filtering allows neural network visualization techniques to visualize the knowledge relationship among different modalitie

关键词： Redundancy

WIT-UAS: A Wildland-fire Infrared Thermal Dataset to Detect Crew Assets From Aerial Views

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jong, Andrew Yu, Mukai Dhrafani, Devansh Kailas, Siva Moon, Brady Sycara, Katia Scherer, Sebastian Carnegie Mellon University School of Computer Science the Robotics Institute 5000 Forbes Ave PittsburghPA United States Carnegie Mellon University College of Engineering Department of Mechanical Engineering 5000 Forbes Ave PittsburghPA United States

We present the Wildland-fire Infrared Thermal (WIT-UAS) dataset for long-wave infrared sensing of crew and vehicle assets amidst prescribed wildland fire environments. While such a dataset is crucial for safety monitoring in wildland fire applications, to the authors’ awareness, no such dataset focusing on assets near fire is publicly available. Presumably, this is due to the barrier to entry of collaborating with fire management personnel. We present two related data subsets: WIT-UAS-ROS consists of full ROS bag files containing sensor and robot data of UAS flight over the fire, and WIT-UAS-Image contains hand-labeled long-wave infrared (LWIR) images extracted from WIT-UAS-ROS. Our dataset is the first to focus on asset detection in a wildland fire environment. We show that thermal detection models trained without fire data frequently detect false positives by classifying fire as people. By adding our dataset to training, we show that the false positive rate is reduced significantly. Yet asset detection in wildland fire environments is still significantly more challenging than detection in urban environments, due to dense obscuring trees, greater heat variation, and overbearing thermal signal of the fire. We publicize this dataset to encourage the community to study more advanced models to tackle this challenging environment. The dataset, code and pretrained models are available at https://***/castacks/WIT-UAS-Dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Infrared devices

SFDA-rPPG: Source-Free Domain Adaptive Remote Physiological Measurement with Spatio-Temporal Consistency

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xie, Yiping Yu, Zitong Wu, Bingjie Xie, Weicheng Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Singapore

Remote Photoplethysmography (rPPG) is a non-contact method that uses facial video to predict changes in blood volume, enabling physiological metrics measurement. Traditional rPPG models often struggle with poor generalization capacity in unseen domains. Current solutions to this problem is to improve its generalization in the target domain through Domain Generalization (DG) or Domain Adaptation (DA). However, both traditional methods require access to both source domain data and target domain data, which cannot be implemented in scenarios with limited access to source data, and another issue is the privacy of accessing source domain data. In this paper, we propose the first Source-free Domain Adaptation benchmark for rPPG measurement (SFDA-rPPG), which overcomes these limitations by enabling effective domain adaptation without access to source domain data. Our framework incorporates a Three-Branch Spatio-Temporal Consistency Network (TSTC-Net) to enhance feature consistency across domains. Furthermore, we propose a new rPPG distribution alignment loss based on the Frequency-domain Wasserstein Distance (FWD), which leverages optimal transport to align power spectrum distributions across domains effectively and further enforces the alignment of the three branches. Extensive cross-domain experiments and ablation studies demonstrate the effectiveness of our proposed method in source-free domain adaptation settings. Our findings highlight the significant contribution of the proposed FWD loss for distributional alignment, providing a valuable reference for future research and applications. The source code is available at https://***/XieYiping66/SFDA-rPPG. Copyright © 2024, The Authors. All rights reserved.

关键词： Photoplethysmography

Development of Fish Separator Conveyor based on Fish Identification System 3

学校读者我要写书评

暂无评论

Development of Fish Separator Conveyor based on Fish Identif...

3rd International Conference on Eco engineering Development, ICEED 2019

作者： Dzulfiqar Agung, Muhammad Rangga Elian, Adrian Adhe Astuti, Winda Puji, Muhammad Nurul Automotive and Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia

Indonesia as the largest archipelago and maritime country in the world has a very large marine resources. Fish is one of the marine wealthties (marine biota), which have large numbers in Indonesia. Fishermen is an important role in the process of fishing, however fish caught by fishermen are often mixed with other types of fish. Currently, the process of fist separation is done manually, which takes longer time and many error occur due to fatigue. In this work the conveyer separator based on the fish identification system is developed. The fish conveyer separator is designed and developed. The fish identification system is based on Fast Fourier Transform (FTT) technique and Artificial Neural Network (ANN). The system is working properly, since it resulting the training and testing accuracy of 80% and 66%, respectively. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Fast Fourier transforms