检索结果-内蒙古大学图书馆

2023 MTS/IEEE U.S. Gulf Coast, OCEANS 2023

作者： Cast, John Dallas Johns Hopkins University Laboratory for Computational Sensing and Robotics BaltimoreMD United States

ISBN: (纸本)9798218142186

The Philippine Coral Reef exhibit within the California Academy of Sciences contains on the order of 100 species of fish and over 1,000 fish. It has multiple visual and auditory aids to help its viewers undertake a more engaged position with respect to it, e.g. live video feeds, kiosks as well as live dive shows in order to educate the audience on both the marine ecosystem represented by the exhibit and the importance of conservation. However, there is little aid that gives the audience live and accurate feedback on the species of fish in front of them. It is difficult as a lay person (often even as a professional) to determine the species of fish they are viewing in the exhibit due to the large number of fish species and fish specimens. This shortcoming is poorly addressed in public aquariums and remains an important issue to properly educate visitors on issues such as conservation and ecological diversity. To facilitate solutions to these problems, we present ***, a platform completed in March 2021, that has taken steps towards greater public engagement and outreach at public aquariums by providing a suite of perception analytics currently including localization and classification for the environments of public aquariums. Using advancements in object recognition and classification for imagery and video data, the practice of transfer learning and modern web development tools, ***, a cloud-hosted platform, serves models for localization and species classification of fish within the Reef Lagoon exhibit at the California Academy of Sciences (∗) using a live webcam of the exhibit. Additionally, it serves data of relevance to ecology and conservation through a simple and powerful interface. We present our curated datasets of and classification/localization models for the fish species within the Reef Lagoon and Philippine Coral Reef exhibits. © 2023 The Marine Technology Society (MTS).

关键词： Fish

来源：评论

学校读者我要写书评

暂无评论

Shape Manipulation of Bevel-Tip Needles for Prostate Biopsy Procedures: A Comparison of Two Resolved-Rate Controllers 46

Shape Manipulation of Bevel-Tip Needles for Prostate Biopsy ...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Wang, Yanzhou Al-Zogbi, Lidia Liu, Jiawei Shepard, Lauren Ghazi, Ahmed Tokuda, Junichi Leonard, Simon Krieger, Axel Iordachita, Iulian Johns Hopkins University Department of Mechanical Engineering The Laboratory for Computational Sensing and Robotics BaltimoreMD United States Johns Hopkins University Laboratory of Computational Sensing and Robotics BaltimoreMD United States Johns Hopkins University Brady Urological Institute BaltimoreMD United States Harvard Medical School Department of Radiology Brigham and Women's Hospital BostonMA United States Johns Hopkins University Laboratory for Computational Sensing and Robotics Department of Computer Science BaltimoreMD United States

ISBN: (纸本)9798350371499

Prostate cancer diagnosis continues to encounter challenges, often due to imprecise needle placement in standard biopsies. Several control strategies have been developed to compensate for needle tip prediction inaccuracies, however none were compared against each other, and it is unclear whether any of them can be safely and universally applied in clinical settings. This paper compares the performance of two resolved-rate controllers, derived from a mechanics-based and a data-driven approach, for bevel-tip needle control using needle shape manipulation through a template. We demonstrate for a simulated 12-core biopsy procedure under model parameter uncertainty that the mechanics-based controller can better reach desired targets when only the final goal configuration is presented even with uncertainty on model parameters estimation, and that providing a feasible needle path is crucial in ensuring safe surgical outcomes when either controller is used for needle shape manipulation. © 2024 IEEE.

关键词： Biopsy

来源：评论

学校读者我要写书评

暂无评论

ClimbAR: Collaborative Augmented Reality for Climbing Applications

ClimbAR: Collaborative Augmented Reality for Climbing Applic...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： John Dallas Cast Alejandro Martin-Gomez Mathias Unberath Laboratory for Computational Sensing and Robotics Johns Hopkins University

ISBN: (数字)9798350374490

ISBN: (纸本)9798350374506

In this work we present ClimbAR an open-source, collaborative, real-time, augmented reality application for the Hololens 2 that al-lows boulderers to set climbing holds virtually to better understand and plan routes. We performed two preliminary studies a quanti-tative study that assessed the system's rotational and translational alignment accuracy and a qualitative study that used surveys and voluntary participation to evaluate the usefulness and enjoyment of the system.

关键词： Surveys Three-dimensional displays Conferences Collaboration User interfaces Real-time systems Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Needle Manipulation Controller Subject to Uncertainty of Tip Pose Feedback: a Simulation Study

Evaluation of Needle Manipulation Controller Subject to Unce...

引用

International Symposium on Medical robotics (ISMR)

作者： Junling Mei Chang Chang Yanzhou Wang Simon Leonard Iulian Iordachita Laboratory of Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA Department of Mechanical Engineering Laboratory of Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA Department of Computer Science Laboratory of Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA

ISBN: (数字)9798331599003

ISBN: (纸本)9798331599010

In this paper, we evaluate the performance of our controller for flexible needle manipulation for percutaneous interventions in a finite element (FE) simulator. We investigate the use of electromagnetic (EM) tracking as needle tip pose feedback, and how artificial sensor noises can affect tracking performance of the controller. In our simulated study, the control system shows high targeting accuracy and robustness with an overall tip position error of 0.49 mm. The addition of needle tip orientation feedback further improves the targeting accuracy for deeper targets, with average error of 0.81 mm when only using position feedback, and 0.55 mm when using additional orientation feedback.

关键词： Target tracking Accuracy Uncertainty Medical robotics Noise Needles Robot sensing systems Robustness Finite element analysis Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Review of Enhanced Handheld Surgical Drills

引用

Critical Reviews in Biomedical Engineering 2023年第6期51卷 29-50页

作者： Usevitch, David E. Bronheim, Rachel S. Cartagena-Reyes, Miguel A. Ortiz-Babilonia, Carlos Margalit, Adam Jain, Amit Armand, Mehran Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD United States Orthopedic Surgery Johns Hopkins University BaltimoreMD United States Department of Orthopedic Surgery Johns Hopkins University BaltimoreMD United States

The handheld drill has been used as a conventional surgical tool for centuries. Alongside the recent successes of surgical robots, the development of new and enhanced medical drills has improved surgeon ability without requiring the high cost and consuming setup times that plague medical robot systems. This work provides an overview of enhanced handheld surgical drill research focusing on systems that include some form of image guidance and do not require additional hardware that physically supports or guides drilling. Drilling is reviewed by main contribution divided into audio-, visual-, or hardware-enhanced drills. A vision for future work to enhance handheld drilling systems is also discussed. © 2023 by Begell House, Inc.

关键词： Drills

来源：评论

学校读者我要写书评

暂无评论

Minimally Invasive Flexible Needle Manipulation Based on Finite Element Simulation and Cross Entropy Method

arXiv

引用

arXiv 2024年

作者： Wang, Yanzhou Chang, Chang Mei, Junling Leonard, Simon Iordachita, Iulian Department of Mechanical Engineering The Laboratory of Computational Sensing and Robotics Johns Hopkins University BaltimoreMD United States Laboratory of Computational Sensing and Robotics Johns Hopkins University BaltimoreMD United States Department of Computer Science The Laboratory of Computational Sensing and Robotics Johns Hopkins University BaltimoreMD United States

We present a novel approach for minimally invasive flexible needle manipulations by pairing a real-time finite element simulator with the cross-entropy method. Additionally, we demonstrate how a kinematic-driven bang-bang controller can complement the control framework for better tracking performance. We show how electromagnetic (EM) tracking can be readily incorporated into the framework to provide controller feedback. Tissue phantom experiment with EM tracking shows the average targeting error is 0.16 ± 0.29mm. © 2024, CC BY-NC-ND.

关键词： Needles

来源：评论

学校读者我要写书评

暂无评论

An Industrial Bin Picking Framework for Assembly Tasks

An Industrial Bin Picking Framework for Assembly Tasks

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Liang, Jizhong Sun, Han Chen, Xinhao Gu, Yuanze Cao, Qixin Shanghai Jiaotong University School of Mechanical Engineering Shanghai200240 China Johns Hopkins University Laboratory for Computational Sensing and Robotics BaltimoreMD21218 United States

ISBN: (纸本)9798350325706

The majority of current bin picking systems, designed for industrial parts, cannot be directly oriented to the downstream task after grasping. This research presents a grasping framework that addresses this challenge by incorporating pose estimation of parts in cluttered bin environments and the targeted design of robot end-effector grippers. This approach ensures that the pose of the part on the gripper is known and fixed, enabling successful assembly tasks in various scenarios. To train an object pose estimation network, we propose a system for generating a dataset of industrial parts using model rendering within a physics engine. We analyze the geometric features of the parts, and further design a gripper, to achieve the grasping strategy. Results demonstrate that for a single known industrial part, the minimum grasping success rate is 91.4% in simulated robot experiments, and the assembly success rates in different scenarios based on this framework exceed 80%. Our framework offers valuable guidance for the deployment of robotic grasping. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of a Needle Manipulation System with EM Tracking for CT-Guided Spinal Injections

Design and Evaluation of a Needle Manipulation System with E...

引用

International Symposium on Medical robotics (ISMR)

作者： Chang Chang Junling Mei Yanzhou Wang Lidia Al-Zogbi Simon Leonard Amit Jain Iulian Iordachita Department of Mechanical Engineering Laboratory of Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA Laboratory of Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA Department of Computer Science Laboratory of Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA Department of Orthopaedic Surgery Johns Hopkins University School of Medicine Baltimore MD USA

ISBN: (数字)9798331599003

ISBN: (纸本)9798331599010

This paper presents a flexible needle guidance system and its workflow that enables registration of computed tomography (CT) and electromagnetic (EM) tracking systems with a finite element (FE) simulator for needle-based percutaneous spinal injections. CT is used only pre- and postoperatively for surgical planning and confirmation, while EM tracking is combined intraoperatively with an FE-based needle controller to track the planned needle trajectory and avoid obstacles. Evaluation of the proposed system using a multi-layer soft tissue phantom shows an average targeting accuracy of 0.4 mm.

关键词： Target tracking Medical robotics Computed tomography Biological tissues Phantoms Needles Trajectory Planning Finite element analysis Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Path Integral Control of I2RIS Robot Using RBF Identifier and Extended Kalman Filter

arXiv

引用

arXiv 2025年

作者： Esfandiari, Mojtaba Du, Pengyuan Wei, Haochen Gehlbach, Peter Munawar, Adnan Kazanzides, Peter Iordachita, Iulian Department of Mechanical Engineering Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Department of Computer Science Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Wilmer Eye Institute Johns Hopkins Hospital BaltimoreMD21287 United States

Modeling and controlling cable-driven snake robots is a challenging problem due to nonlinear mechanical properties such as hysteresis, variable stiffness, and unknown friction between the actuation cables and the robot body. This challenge is more significant for snake robots in ophthalmic surgery applications, such as the Improved Integrated Robotic Intraocular Snake (I2RIS), given its small size and lack of embedded sensory feedback. Data-driven models take advantage of global function approximations, reducing complicated analytical models’ challenge and computational costs. However, their performance might deteriorate in case of new data unseen in the training phase. Therefore, adding an adaptation mechanism might improve these models’ performance during snake robots’ interactions with unknown environments. In this work, we applied a model predictive path integral (MPPI) controller on a data-driven model of the I2RIS based on the Gaussian mixture model (GMM) and Gaussian mixture regression (GMR). To analyze the performance of the MPPI in unseen robot-tissue interaction situations, unknown external disturbances and environmental loads are simulated and added to the GMM-GMR model. These uncertainties of the robot model are then identified online using a radial basis function (RBF) whose weights are updated using an extended Kalman filter (EKF). Simulation results demonstrated the robustness of the optimal control solutions of the MPPI algorithm and its computational superiority over a conventional model predictive control (MPC) algorithm. © 2025, CC BY.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

***: Towards Development, Deployment and Distribution of Novel Artificial Intelligence for Aquariums

***: Towards Development, Deployment and Distribution of Nov...

引用

OCEANS

作者： John Dallas Cast Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore MD USA

The Philippine Coral Reef exhibit within the California Academy of Sciences contains on the order of 100 species of fish and over 1,000 fish. It has multiple visual and auditory aids to help its viewers undertake a more engaged position with respect to it, e.g. live video feeds, kiosks as well as live dive shows in order to educate the audience on both the marine ecosystem represented by the exhibit and the importance of conservation. However, there is little aid that gives the audience live and accurate feedback on the species of fish in front of them. It is difficult as a lay person (often even as a professional) to determine the species of fish they are viewing in the exhibit due to the large number of fish species and fish specimens. This shortcoming is poorly addressed in public aquariums and remains an important issue to properly educate visitors on issues such as conservation and ecological diversity. To facilitate solutions to these problems, we present ***, a platform completed in March 2021, that has taken steps towards greater public engagement and outreach at public aquariums by providing a suite of perception analytics currently including localization and classification for the environments of public aquariums. Using advancements in object recognition and classification for imagery and video data, the practice of transfer learning and modern web development tools, ***, a cloud-hosted platform, serves models for localization and species classification of fish within the Reef Lagoon exhibit at the California Academy of Sciences (*) using a live webcam of the exhibit. Additionally, it serves data of relevance to ecology and conservation through a simple and powerful interface. We present our curated datasets of and classification/localization models for the fish species within the Reef Lagoon and Philippine Coral Reef exhibits.

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：