检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6225-6239页

作者： Teng, Fei Zhang, Jiaming Peng, Kunyu Wang, Yaonan Stiefelhagen, Rainer Yang, Kailun Hunan University School of Robotics National Engineering Research Center of Robot Visual Perception and Control Technology Changsha410082 China Karlsruhe Institute of Technology Institute for Anthropomatics and Robotics Karlsruhe76131 Germany Institute for Visual Computing ETH Zurich Zurich8092 Switzerland

Light field cameras are capable of capturing intricate angular and spatial details. This allows for acquiring complex light patterns and details from multiple angles, significantly enhancing the precision of image semantic segmentation. However, two significant issues arise: 1) The extensive angular information of light field cameras contains a large amount of redundant data, which is overwhelming for the limited hardware resources of intelligent agents. 2) A relative displacement difference exists in the data collected by different microlenses. To address these issues, we propose an omni-aperture fusion model (OAFuser) that leverages dense context from the central view and extracts the angular information from subaperture images to generate semantically consistent results. To simultaneously streamline the redundant information from the light field cameras and avoid feature loss during network propagation, we present a simple yet very effective subaperture fusion module (SAFM). This module efficiently embeds subaperture images in angular features, allowing the network to process each subaperture image with a minimal computational demand of only (∼1\rm GFlops). Furthermore, to address the mismatched spatial information across viewpoints, we present a center angular rectification module (CARM) to realize feature resorting and prevent feature occlusion caused by misalignment. The proposed OAFuser achieves state-of-the-art performance on four UrbanLF datasets in terms of all evaluation metrics and sets a new record of 84.93% in mIoU on the UrbanLF-Real Extended dataset, with a gain of +3.69%. The source code for OAFuser is available at https://***/FeiBryantkit/OAFuser. © 2020 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Leveraging Human Input to Enable Robust, Interactive, and Aligned AI Systems 39

Leveraging Human Input to Enable Robust, Interactive, and Al...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Brown, Daniel S. Kahlert School of Computing Robotics Center University of Utah United States

ISBN: (纸本)157735897X

Ensuring that AI systems do what we, as humans, actually want them to do, is one of the biggest open research challenges in AI alignment and safety. My research seeks to directly address this challenge by enabling AI systems to interact with humans to learn aligned and robust behaviors. The way robots and other AI systems behave is often the result of optimizing a reward function. However, manually designing good reward functions is highly challenging and error prone, even for domain experts. Although reward functions are often difficult to manually specify, human feedback in the form of demonstrations or preferences is often much easier to obtain. However, human data is often difficult to interpret due to ambiguity and noise. Thus, it is critical that AI systems take into account epistemic uncertainty over the human’s true intent. My talk will give an overview of my lab’s progress along the following fundamental research areas: (1) efficiently maintaining uncertainty over human intent, (2) directly optimizing behavior to be robust to uncertainty over human intent, and (3) actively querying for additional human input to reduce uncertainty over human intent. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Human engineering

来源：评论

学校读者我要写书评

暂无评论

V-TX: A VR-Based Deployment and Evaluation System for Wearable Telexistence Robotic Systems 23

V-TX: A VR-Based Deployment and Evaluation System for Wearab...

引用

23rd International Conference on Cyberworlds, CW 2024

作者： Iskandar, Abdullah Aburajouh, Hala Khazer Shebli Al-Shaer, Eman Hussain Al-Yafei, Fatima Thabit Al-Arqaban, Bushra Ahmad Al-Yousef, Moneera Yang, Pinchu Halabi, Osama Al-Sada, Mohammed Nakajima, Tatsuo Waseda University Computer Science and Engineering Japan Telkom University School of Computing Indonesia Qatar University Computer Science and Engineering Qatar Waseda University Future Robotics Organization Japan Qatar University KINDI Computing Research Center Qatar

ISBN: (纸本)9798331527174

Wearable telexistence robotic systems have risen in prominence after the COVID-19 pandemic, being vital for various applications. However, their design, fabrication, and evaluation require substantial resources and are unsupported by robot simulation systems. Therefore, we present V-TX, which is a VR-based system for deploying and evaluating wearable telexistence systems. V-TX extends key telexistence systems' components with versatility for customizing different attributes based on the intended application. To demonstrate the potential of V-TX, we replicated a real telexistence robot in V-TX, called Piton, and showed a novel potential use for exploring and evaluating different robot designs, interaction methods, and deployments. We conducted a comparative evaluation between the real Piton robot and its V-TX implementation. The results show that V-TX gave results that match those of the real counterpart across the main factors of telexistence, indicating its viability as an alternative to traditional evaluation approaches using real robots. Lastly, we discuss the limitations and present future research directions. © 2024 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

LF-PGVIO: A Visual-Inertial-Odometry Framework for Large Field-of-View Cameras using Points and Geodesic Segments

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Wang, Ze Yang, Kailun Shi, Hao Zhang, Yufan Xu, Zhijie Gao, Fei Wang, Kaiwei State Key Laboratory of Extreme Photonics and Instrumentation School of Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha China School of Computing and Engineering University of Huddersfield Huddersfield U.K State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

In this paper, we propose LF-PGVIO, a Visual-Inertial-Odometry (VIO) framework for large Field-of-View (FoV) cameras with a negative plane using points and geodesic segments. The purpose of our research is to unleash the potential of point-line odometry with large-FoV omnidirectional cameras, even for cameras with negative-plane FoV. To achieve this, we propose an Omnidirectional Curve Segment Detection (OCSD) method combined with a camera model which is applicable to images with large distortions, such as panoramic annular images, fisheye images, and various panoramic images. The geodesic segment is sliced into multiple straight-line segments based on the radian and descriptors are extracted and recombined. Descriptor matching establishes the constraint relationship between 3D line segments in multiple frames. In our VIO system, line feature residual is also extended to support large-FoV cameras. Extensive evaluations on public datasets demonstrate the superior accuracy and robustness of LF-PGVIO compared to state-of-the-art methods. The source code will be made publicly available at https://***/flysoaryun/LF-PGVIO. IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Leveraging Graph Neural Networks in Transferring Multimodal Knowledge for Unimodal Segmentation 22

Leveraging Graph Neural Networks in Transferring Multimodal ...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Liu, Tianyi Wang, Jiongshu Jiang, Haochuan Huang, Kaizhu School of Robotics Xi'an Jiaotong-Liverpool University China School of Computing and Mathematical Sciences University of Leicester United Kingdom Duke Kunshan University Data Science Research Center China

ISBN: (纸本)9798331520526

Accurate segmentation of brain tumors in MRI scans is crucial for effective treatment. Multimodal MRI, including FLAIR, Tlce, T1, and T2 images, provides valuable infor-mation for tumor delineation. However, challenges such data corruption and varying protocols can lead to missing modal-ities, affecting segmentation accuracy. Recent methods at-tempt to transfer knowledge from multimodal teacher mod-els to unimodal student models, but often struggle to capture complex structural relationships within the data. This paper introduces a novel approach called Graph Neural Network-based Knowledge Distillation (GKD), which uses Graph Neu-ral Networks to create a comprehensive graph connecting in-termediate layers of both teacher and student networks. This enables the student network to better learn essential features and their interactions. Evaluations on the BraTS2018 and BraTS2020 datasets demonstrate that GKD significantly en-hances brain tumor segmentation accuracy by deepening the connection between teacher and student insights. The code is publicly available at https://***/T-Y-Liu/GKD. © 2025 IEEE.

关键词： Brain Tumor Segmentation Knowledge Distillation Magnetic Resonance Imaging Missing Modality

来源：评论

学校读者我要写书评

暂无评论

23 DoF Grasping Policies from a Raw Point Cloud

arXiv

引用

arXiv 2024年

作者： Matak, Martin Van Wyk, Karl Hermans, Tucker School of Computing Robotics Center University of Utah United States NVIDIA United States

Coordinating the motion of robots with high degrees of freedom (DoF) to grasp objects gives rise to many challenges. In this paper, we propose a novel imitation learning approach to learn a policy that directly predicts 23 DoF grasp trajectories from a partial point cloud provided by a single, fixed camera. At the core of the approach is a second-order geometric-based model of behavioral dynamics. This Neural Geometric Fabric (NGF) policy predicts accelerations directly in joint space. We show that our policy is capable of generalizing to novel objects, and combine our policy with a geometric fabric motion planner in a loop to generate stable grasping trajectories. We evaluate our approach on a set of three different objects, compare different policy structures, and run ablation studies to understand the importance of different object encodings for policy learning. © 2024, CC BY-NC-SA.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Efficient and Accurate Mapping of Subsurface Anatomy via Online Trajectory Optimization for Robot Assisted Surgery

Efficient and Accurate Mapping of Subsurface Anatomy via Onl...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Brian Y. Cho Alan Kuntz Robotics Center and Kahlert School of Computing University of Utah Salt Lake City UT USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Robotic surgical subtask automation has the potential to reduce the per-patient workload of human surgeons. There are a variety of surgical subtasks that require geometric information of subsurface anatomy, such as the location of tumors, which necessitates accurate and efficient surgical sensing. In this work, we propose an automated sensing method that maps 3D subsurface anatomy to provide such geometric knowledge. We model the anatomy via a Bayesian Hilbert map-based probabilistic 3D occupancy map. Using the 3D occupancy map, we plan sensing paths on the surface of the anatomy via a graph search algorithm, A * search, with a cost function that enables the trajectories generated to balance between exploration of unsensed regions and refining the existing probabilistic understanding. We demonstrate the performance of our proposed method by comparing it against 3 different methods in several anatomical environments including a real-life CT scan dataset. The experimental results show that our method efficiently detects relevant subsurface anatomy with shorter trajectories than the comparison methods, and the resulting occupancy map achieves high accuracy.

关键词： Accuracy Three-dimensional displays Medical robotics Costs Computed tomography Robot sensing systems Probabilistic logic

来源：评论

学校读者我要写书评

暂无评论

Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery

Reward Learning from Suboptimal Demonstrations with Applicat...

引用

International Symposium on Medical robotics (ISMR)

作者： Zohre Karimi Shing-Hei Ho Bao Thach Alan Kuntz Daniel S. Brown Robotics Center and the Kahlert School of Computing at the University of Utah Salt Lake City UT USA

ISBN: (数字)9798350377118

ISBN: (纸本)9798350377125

Automating robotic surgery via learning from demonstration (LfD) techniques is extremely challenging. This is because surgical tasks often involve sequential decision-making processes with complex interactions of physical objects and have low tolerance for mistakes. Prior works assume that all demonstrations are fully observable and optimal, which might not be practical in the real world. This paper introduces a sample-efficient method that learns a robust reward function from a limited amount of ranked suboptimal demonstrations consisting of partial-view point cloud observations. The method then learns a policy by optimizing the learned reward function using reinforcement learning (RL). We show that using a learned reward function to obtain a policy is more robust than pure imitation learning. We apply our approach on a physical surgical electrocautery task and demonstrate that our method can perform well even when the provided demonstrations are suboptimal and the observations are high-dimensional point clouds. Code and videos available here: https://***/viewllfdinelectrocautery

关键词： Point cloud compression Medical robotics Codes Imitation learning Decision making Surgery Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Modeling Kinematic Uncertainty of Tendon-Driven Continuum Robots via Mixture Density Networks

Modeling Kinematic Uncertainty of Tendon-Driven Continuum Ro...

引用

International Symposium on Medical robotics (ISMR)

作者： Jordan Thompson Brian Y. Cho Daniel S. Brown Alan Kuntz Robotics Center and the Kahlert School of Computing at the University of Utah Salt Lake City UT USA

ISBN: (数字)9798350377118

ISBN: (纸本)9798350377125

Tendon-driven continuum robot kinematic models are frequently computationally expensive, inaccurate due to unmodeled effects, or both. In particular, unmodeled effects produce uncertainties that arise during the robot's operation that lead to variability in the resulting geometry. We propose a novel solution to these issues through the development of a Gaussian mixture kinematic model. We train a mixture density network to output a Gaussian mixture model representation of the robot geometry given the current tendon displacements. This model computes a probability distribution that is more representative of the true distribution of geometries at a given configuration than a model that outputs a single geometry, while also reducing the computation time. We demonstrate one use of this model through a trajectory optimization method that explicitly reasons about the workspace uncertainty to minimize the probability of collision.

关键词： Geometry Uncertainty Computational modeling Process control Kinematics Planning Continuum robots

来源：评论

学校读者我要写书评

暂无评论

Learning Generalizable Language-Conditioned Cloth Manipulation from Long Demonstrations

arXiv

引用

arXiv 2025年

作者： Zhao, Hanyi Zhu, Jinxuan Yan, Zihao Li, Yichen Deng, Yuhong Wang, Xueqian Center for Artificial Intelligence and Robotics Tsinghua Shenzhen International Graduate School Shenzhen China School of Computing National University of Singapore Singapore

Multi-step cloth manipulation is a challenging problem for robots due to the high-dimensional state spaces and the dynamics of cloth. Despite recent significant advances in end-to-end imitation learning for multi-step cloth manipulation skills, these methods fail to generalize to unseen tasks. Our insight in tackling the challenge of generalizable multi-step cloth manipulation is decomposition. We propose a novel pipeline that autonomously learns basic skills from long demonstrations and composes learned basic skills to generalize to unseen tasks. Specifically, our method first discovers and learns basic skills from the existing long demonstration benchmark with the commonsense knowledge of a large language model (LLM). Then, leveraging a high-level LLM-based task planner, these basic skills can be composed to complete unseen tasks. Experimental results demonstrate that our method outperforms baseline methods in learning multi-step cloth manipulation skills for both seen and unseen tasks. Project website: https://***/view/gen-cloth Copyright © 2025, The Authors. All rights reserved.

关键词： Demonstrations

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：