检索结果-内蒙古大学图书馆

Neural Augmentation Based Panoramic High Dynamic Range Stitching

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zheng, Chaobing Xu, Yilun Chen, Weihai Wu, Shiqian Zhang, Sen Li, Zhengguo Institute of Robotics and Intelligent Systems School of Electronic Information Wuhan University of Science and Technology 947 Heping Avenue Wuhan430081 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China School of Automation and Electrical Engineering University of Science and Technology Beiing Beijing100083 China Key Laboratory of Knowledge Auomalion for indusrial Proceses of Mimistry ofEducation University of Science and Techmology Beijing Beijing1083 China Shunde lnnovation School University of Science and Technology Beijing Foshan 528300 China VI Department Institute for Infocomm Research A*STAR 138632 Singapore

Due to saturated regions of inputting low dynamic range (LDR) images and large intensity changes among the LDR images caused by different exposures, it is challenging to produce an information enriched panoramic LDR image without visual artifacts for a high dynamic range (HDR) scene through stitching multiple geometrically synchronized LDR images with different exposures and pairwise overlapping fields of views (OFOVs). Fortunately, the stitching of such images is innately a perfect scenario for the fusion of a physics-driven approach and a data-driven approach due to their OFOVs. Based on this new insight, a novel neural augmentation based panoramic HDR stitching algorithm is proposed in this paper. The physics-driven approach is built up using the OFOVs. Different exposed images of each view are initially generated by using the physics-driven approach, are then refined by a data-driven approach, and are finally used to produce panoramic LDR images with different exposures. All the panoramic LDR images with different exposures are combined together via a multi-scale exposure fusion algorithm to produce the final panoramic LDR image. Experimental results demonstrate the proposed algorithm outperforms existing panoramic stitching algorithms. © 2024, CC0.

关键词： Image fusion

Incremental Non-Gaussian Inference for SLAM Using Normalizing Flows

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Qiangqiang Pu, Can Khosoussi, Kasra Rosen, David M. Fourie, Dehann How, Jonathan P. Leonard, John J. MIT Computer Science and Artificial Intelligence Laboratory CambridgeMA02139 United States MIT Department of Nuclear Science and Engineering CambridgeMA02139 United States Robotics and Autonomous Systems Group DATA61 CSIRO BrisbaneQLD4069 Australia Northeastern University Department of Electrical and Computer Engineering BostonMA02115 United States NavAbility BostonMA02110 United States MIT Department of Aeronautical and Astronautical Engineering CambridgeMA02139 United States

This paper presents normalizing flows for incremental smoothing and mapping (NF-iSAM), a novel algorithm for inferring the full posterior distribution in SLAM problems with nonlinear measurement models and non-Gaussian factors. NF-iSAM exploits the expressive power of neural networks, and trains normalizing flows to model and sample the full posterior. By leveraging the Bayes tree, NF-iSAM enables efficient incremental updates similar to iSAM2, albeit in the more challenging non-Gaussian setting. We demonstrate the advantages of NF-iSAM over state-of-the-art point and distribution estimation algorithms using range-only SLAM problems with data association ambiguity. NF-iSAM presents superior accuracy in describing the posterior beliefs of continuous variables (e.g., position) and discrete variables (e.g., data association). Copyright © 2021, The Authors. All rights reserved.

关键词： Gaussian noise (electronic)

IVS O5: New developments and research trends for intelligent vehicles

学校读者我要写书评

暂无评论

IEEE Intelligent systems 2005年第4期20卷 10-14页

作者： Wang, Fei-Yue Li, Li Song, Jingyan Niehsen, Wolfgang Zheng, Nan-Ning University of Arizona Chinese Academy of Science United States University of Arizona United States Tsinghua University China Chinese Academy of Sciences China Robert Bosch Corporate Research United States Xi'an Jiaotong University China Department of Automation Tsinghua University Beijing China University of Arizona's Systems Industrial Engineering Department United States University's Program in Advanced Research of Complex Systems United States Key Laboratory of Complex Systems and Intelligence Science Chinese Academy of Sciences China Robert Bosch Corporate Research United States Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University China

Recent advances and research trends for intelligent vehicles were studied. Vehicle-state sensing focuses on measuring a vehicle's movement and monitoring its actuators. Individual-vehicle-control research focuses mainly on guaranteeing driving safety. The results suggest that intervehicle, vehicle-roadside, and vehicle-driver information sharing currently the most attractive trend in intelligent-vehicle research.

关键词： Intelligent vehicle highway systems

Coordinated Guiding Vector Field Design for Ordering-Flexible Multi-Robot Surface Navigation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Bin-Bin Zhang, Hai-Tao Yao, Weijia Sun, Zhiyong Cao, Ming The School of Artificial Intelligence and Automation The Engineering Research Center of Autonomous Intelligent Unmanned Systems The Key Laboratory of Image Processing and Intelligent Control The State Key Lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China The School of Robotics Hunan University Hunan410082 China The Institute of Engineering and Technology University of Groningen Groningen9747 AG Netherlands Department of Electrical Engineering Eindhoven University of Technology Netherlands

We design a distributed coordinated guiding vector field (CGVF) for a group of robots to achieve ordering-flexible motion coordination while maneuvering on a desired two-dimensional (2D) surface. The CGVF is characterized by three terms, i.e., a convergence term to drive the robots to converge to the desired surface, a propagation term to provide a traversing direction for maneuvering on the desired surface, and a coordinated term to achieve the surface motion coordination with an arbitrary ordering of the robotic group. By setting the surface parameters as additional virtual coordinates, the proposed approach eliminates potential singularity of the CGVF and enables both the global convergence to the desired surface and the maneuvering on the surface from all possible initial conditions. The ordering-flexible surface motion coordination is realized by each robot to share with its neighbors only two virtual coordinates, i.e. that of a given target and that of its own, which reduces the communication and computation cost in multi-robot surface navigation. Finally, the effectiveness of the CGVF is substantiated by extensive numerical simulations. Copyright © 2024, The Authors. All rights reserved.

关键词： Navigation

Enhanced Visual Feedback with Decoupled Viewpoint Control in Immersive Humanoid Robot Teleoperation using SLAM

学校读者我要写书评

暂无评论

Enhanced Visual Feedback with Decoupled Viewpoint Control in...

IEEE-RAS International Conference on Humanoid Robots

作者： Yang Chen Leyuan Sun Mehdi Benallegue Rafael Cisneros-Limón Rohan P. Singh Kenji Kaneko Arnaud Tanguy Guillaume Caron Kenji Suzuki Abderrahmane Kheddar Fumio Kanehiro School of Integrative and Global Majors (SIGMA) University of Tsukuba Japan CNRS-AIST JRL (Joint Robotics Laboratory) IRL National Institute of Advanced Industrial Science and Technology (AIST) Department of Intelligent and Mechanical Interaction Systems Graduate School of Science and Technology University of Tsukuba Japan MIS lab Universite de Picardie Jules Verne Amiens France Faculty of Engineering and Center for Cybernetics Research University of Tsukuba Japan

ISBN: (数字)9798350309799

ISBN: (纸本)9798350309805

In immersive humanoid robot teleoperation, there are three main shortcomings that can alter the transparency of the visual feedback: (i) the lag between the motion of the operator's and robot's head due to network communication delays or slow robot joint motion. This latency could cause a noticeable delay in the visual feedback, which jeopardizes the embodiment quality, can cause dizziness, and affects the interactivity resulting in operator frequent motion pauses for the visual feedback to settle; (ii) the mismatch between the camera's and the headset's field-of-views (FOV), the former having generally a lower FOV; and (iii) a mismatch between human's and robot's range of motions of the neck, the latter being also generally lower. In order to leverage these draw-backs, we developed a decoupled viewpoint control solution for a humanoid platform which allows visual feedback with low-latency and artificially increases the camera's FOV range to match that of the operator's headset. Our novel solution uses SLAM technology to enhance the visual feedback from a reconstructed mesh, complementing the areas that are not covered by the visual feedback from the robot. The visual feedback is presented as a point cloud in real-time to the operator. As a result, the operator is fed with real-time vision from the robot's head orientation by observing the pose of the point cloud. Balancing this kind of awareness and immersion is important in virtual reality based teleoperation, considering the safety and robustness of the control system. An experiment shows that the effectiveness of our solution.

关键词： Point cloud compression Visualization Simultaneous localization and mapping Humanoid robots Virtual reality Real-time systems Robustness

ROBOTIC AND ARTIFICIAL-INTELLIGENCE systems FOR THE NAVAL OPERATIONAL ENVIRONMENT

学校读者我要写书评

暂无评论

NAVAL ENGINEERS JOURNAL 1987年第4期99卷 74-86页

作者： HOGGE, SM The author earned her bachelor's of science degree in industrial engineering and operations research from Virginia Polytechnic Institute and State University. While at Virginia Tech she worked in the Robotics Laboratory supporting robotics research sponsored by the National Bureau of Standards. She completed her master's of science in computer science at The Johns Hopkins University. Until this past March Miss Hogge worked at the Naval Surface Weapons Center in Silver Spring Maryland. Her duties included the application of robotics and artificial intelligence to explosive ordnance disassembly mobile robotics remote controlled fire fighting vehicles human factors expert systems computer enhanced decision-making aids and hardware security. She published a two-volume study discussing shipboard operational applications of robotics and AI. In addition her publications include nine recent journal articles on robotics and computer security. Miss Hogge is currently employed with Automaker Inc. in Houston Texas. Her current role is manager of all government related robotic operations and vision systems. Miss Hogge's projects at Automaker include: an explosive ordnance disassembly gantry robot system a vision inspection system to examine bearings 3-part camouflage spray painting an investigation of the use of robotic welding in Navy shipyards and rework facilities and epoxy spray painting of missile radomes.

Due to demographical factors, there will be a 25% decline in the national labor pool of eligible 17 to 21 year old men by 1992. As the Navy faces fierce competition with other services and private industry for the dwindling personnel resources of the nation, efforts must be made to consider automating certain tasks, especially those that are hazardous, boring, and labor intensive onboard ships at sea. The Surface Ship Continuing Concept Formulation (CONFORM) Program (SEA-5014) sponsored the Naval Surface Weapons Center's robotics laboratory to identify potential applications of robotic and artificial intelligence systems to operation and mission activities for shipboard use. The results of the investigation concerning applications of robotics to automate the aforementioned tasks are presented. Changes in current manning levels for selected tasks and ship classes, i.e., CVs, CVNs, LPDs, LPNs, and auxiliaries are examined. Future ship designs incorporating robotics, such as the advance based repair (ABR) ship are discussed. Twenty-four applications were cited in the study which include a remote controlled vehicle for flight deck operations, limited tasks in biological, chemical, and radiation environments, computer aided command decision aids, ordnance handling, undersea search, recovery, and salvage, and ventilation duct cleaning. Four of the applications and their subsequent hardware fruition will be discussed.

关键词： robotics

One to many: Adaptive instrument segmentation via meta learning and dynamic online adaptation in robotic surgical video

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhao, Zixu Jin, Yueming Lu, Bo Ng, Chi-Fai Dou, Qi Liu, Yun-Hui Heng, Pheng-Ann The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The T Stone Robotics Institute The Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China The Department of Surgery The Chinese University of Hong Kong Hong Kong

Surgical instrument segmentation in robot-assisted surgery (RAS) - especially that using learning-based models - relies on the assumption that training and testing videos are sampled from the same domain. However, it is impractical and expensive to collect and annotate sufficient data from every new domain. To greatly increase the label efficiency, we explore a new problem, i.e., adaptive instrument segmentation, which is to effectively adapt one source model to new robotic surgical videos from multiple target domains, only given the annotated instruments in the first frame. We propose MDAL, a meta-learning based dynamic online adaptive learning scheme with a two-stage framework to fast adapt the model parameters on the first frame and partial subsequent frames while predicting the results. MDAL learns the general knowledge of instruments and the fast adaptation ability through the video-specific meta-learning paradigm. The added gradient gate excludes the noisy supervision from pseudo masks for dynamic online adaptation on target videos. We demonstrate empirically that MDAL outperforms other state-of-the-art methods on two datasets (including a real-world RAS dataset). The promising performance on ex-vivo scenes also benefits the downstream tasks such as robot-assisted suturing and camera control. Copyright © 2021, The Authors. All rights reserved.

关键词： Surgical equipment

Graphical Characterizations for Structural Controllability of Drifted Bilinear systems

学校读者我要写书评

暂无评论

Graphical Characterizations for Structural Controllability o...

IEEE Conference on Decision and Control

作者： Xing Wang Bo Li Jr-Shin Li Ian R. Petersen Guodong Shi Key Laboratory of Mathematics Mechanization Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China Washington University St. Louis MO USA Research School of Engineering Australian National University Canberra ACT Australia Australian Center for Field Robotics School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney NSW Australia

ISBN: (纸本)9781665436601

In this paper, we study graphical conditions for structural controllability and accessibility of drifted bilinear systems over Lie groups. We consider a bilinear control system with drift and controlled terms that evolves over the special orthogonal group and the special unitary group. Zero patterns are prescribed for the drift and controlled dynamics with respect to a set of base elements in the corresponding Lie algebra. The drift dynamics must respect a rigid zero- pattern in the sense that the drift takes values as a linear combination of base elements with strictly non-zero coefficients; the controlled dynamics are allowed to follow a free zero pattern with potentially zero coefficients in the configuration of the controlled term by linear combination of the controlled base elements. First of all, for such bilinear systems over the special orthogonal group, the zero patterns are shown to be associated with two undirected graphs whose connectivity and connected components ensure structural controllability. Next, for bilinear systems over the special unitary group, we introduce two edge- colored graphs associated with the drift and controlled zero patterns, and prove structural controllability conditions related to connectivity and the number of edges of a particular color.

关键词： Algebra Conferences Color Controllability Nonlinear systems Computational complexity

Position control of XY precision planar motion table based on input shaping filter

学校读者我要写书评

暂无评论

Position control of XY precision planar motion table based o...

International Conference on Electronics, Communications and Information Technology (CECIT)

作者： HuaLiang Zhang Xu Lu DanPing Jia BingJie Zhao Tao Zhang Yang Liu HongYu Yan Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China School of Artificial Intelligence Shenyang University of Technology Shenyang China School of Information Science and Engineering Shenyang University of Technology Shenyang China

ISBN: (纸本)9781665437585

In order to solve the vibration problem of mining equipment, a Simulink simulation model of current loop, speed loop and position loop of permanent magnet synchronous motor was established to track the input position signal of the motor system.[1] At the same time, the input shaper is introduced into the motor three loop control model to study the vibration suppression effect of the input shaper.[2] The essence of the input shaper is to filter the input signal. Usually, the parameters of the input shaper need to be accurately identified and the detailed parameters of the system need to be identified. However, the problem that the identification accuracy of the system is not enough often makes the parameters of the shaper uncertain. In view of the problem that the system identification is not accurate, a method of adjusting and setting input shaper parameters is designed, which is not very dependent on the system. The results show that the optimal parameters of the shaper can be selected by the method. Compared with the parameters of the shaper selected according to the identification model, the vibration suppression effect is better.

关键词： Vibrations Analytical models Tracking loops Software packages Magnetic separation Transfer functions Position control