检索结果-内蒙古大学图书馆

EdgeFlowNet: 100FPS@1W Dense Optical Flow for Tiny Mobile Robots

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第1期10卷 128-135页

作者： Pinnama Raju, Sai Ramana Kiran Singh, Rishabh Velmurugan, Manoj Jagannatha Sanket, Nitin Worcester Polytech Inst Percept & Autonomous Robot PeAR Grp Robot Engn Worcester MA 01609 USA

Optical flow estimation is a critical task for tiny mobile robotics to enable safe and accurate navigation, obstacle avoidance, and other functionalities. However, optical flow estimation on tiny robots is challenging due to limited onboard sensing and computation capabilities. In this letter, we propose EdgeFlowNet, a high-speed, low-latency dense optical flow approach for tiny autonomous mobile robots by harnessing the power of edge computing. We demonstrate the efficacy of our approach by deploying EdgeFlowNet on a tiny quadrotor to perform static obstacle avoidance, flight through unknown gaps and dynamic obstacle dodging. EdgeFlowNet is about 20x faster than the previous state-of-the-art approaches while improving accuracy by over 20% and using only 1.08 W of power enabling advanced autonomy on palm-sized tiny mobile robots.

关键词： Aerial systems perception and autonomy deep learning for visual perception deep learning for visual perception deep learning deep learning edge computing edge computing optical flow optical flow quadrotors quadrotors vision-based navigation vision-based navigation

来源：评论

学校读者我要写书评

暂无评论

Stereo-Based 3D Human Pose Estimation for Underwater Robots Without 3D Supervision

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第5期10卷 5002-5009页

作者： Wu, Ying-Kun Sattar, Junaed Univ Minnesota Twin Cities Dept Comp Sci & Engn Minneapolis MN 55455 USA Univ Minnesota Twin Cities Minnesota Robot Inst MnRI Minneapolis MN 55455 USA

In this paper, we propose a novel deep learning-based 3D underwater human pose estimator capable of providing metric 3D poses of scuba divers from stereo image pairs. While existing research has made significant advancements in 3D human pose estimation, most methods rely on 3D ground truth for training, which is challenging to acquire in dynamic environments where traditional motion capture systems are impractical to deploy. To overcome this, our approach leverages epipolar geometry to derive 3D information from 2D estimations. Our method estimates semantic keypoints while capturing their corresponding disparity from binocular perspectives, thus avoiding challenges in calibrating for multi-view setups or scale-ambiguity in monocular settings. Additionally, to reduce the sensitivity of our method to 2D annotation accuracy, we propose an auto-refinement pipeline to automatically correct biases introduced by human labeling. Experiments demonstrate that our approach significantly improves performance compared to previous state-of-the-art methods in different environments, including but not limited to underwater scenarios, while being efficient enough to run on limited-capacity edge devices.

关键词： Marine robotics gesture posture and facial expressions deep learning for visual perception deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

MonoTher-Depth: Enhancing Thermal Depth Estimation via Confidence-Aware Distillation

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第3期10卷 2830-2837页

作者： Zuo, Xingxing Ranganathan, Nikhil Lee, Connor Gkioxari, Georgia Chung, Soon-Jo CALTECH Pasadena CA 91125 USA

Monocular depth estimation (MDE) from thermal images is a crucial technology for robotic systems operating in challenging conditions such as fog, smoke, and low light. The limited availability of labeled thermal data constrains the generalization capabilities of thermal MDE models compared to foundational RGB MDE models, which benefit from datasets of millions of images across diverse scenarios. To address this challenge, we introduce a novel pipeline that enhances thermal MDE through knowledge distillation from a versatile RGB MDE model. Our approach features a confidence-aware distillation method that utilizes the predicted confidence of the RGB MDE to selectively strengthen the thermal MDE model, capitalizing on the strengths of the RGB model while mitigating its weaknesses. Our method significantly improves the accuracy of the thermal MDE, independent of the availability of labeled depth supervision, and greatly expands its applicability to new scenarios. In our experiments on new scenarios without labeled depth, the proposed confidence-aware distillation method reduces the absolute relative error of thermal MDE by 22.88% compared to the baseline without distillation.

关键词： Predictive models Cameras Training Measurement Depth measurement Adaptation models Metadata Feature extraction Accuracy Uncertainty deep learning for visual perception range sensing thermal camera

来源：评论

学校读者我要写书评

暂无评论

Exploiting Motion Prior for Accurate Pose Estimation of Dashboard Cameras

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第1期10卷 764-771页

作者： Lu, Yipeng Zhao, Yifan Wang, Haiping Ruan, Zhiwei Liu, Yuan Dong, Zhen Yang, Bisheng Wuhan Univ State Key Lab Informat Engn Surveying Mapping & Re Wuhan 430072 Peoples R China China Univ Geosci Wuhan 430079 Peoples R China Didi Chuxing Technol Co Beijing 100193 Peoples R China Hong Kong Univ Sci & Technol Hong Kong Peoples R China Nanyang Technol Univ Singapore 639798 Singapore

Dashboard cameras (dashcams) record millions of driving videos daily, offering a valuable potential data source for various applications, including driving map production and updates. A necessary step for utilizing these dashcam data involves the estimation of camera poses. However, the low-quality images captured by dashcams, characterized by motion blurs and dynamic objects, pose challenges for existing image-matching methods in accurately estimating camera poses. In this study, we propose a precise pose estimation method for dashcam images, leveraging the inherent camera motion prior. Typically, image sequences captured by dash cameras exhibit pronounced motion prior, such as forward movement or lateral turns, which serve as essential cues for correspondence estimation. Building upon this observation, we devise a pose regression module aimed at learning camera motion prior, subsequently integrating these prior into both correspondences and pose estimation processes. The experiment shows that, in real dashcams dataset, our method is 22% better than the baseline for pose estimation in AUC5 degrees, and it can estimate poses for 19% more images with less reprojection error in Structure from Motion (SfM).

关键词： Cameras Pose estimation Accuracy Feature extraction Estimation Image coding Videos Neural networks Dynamics Vectors Computer vision for transportation deep learning for visual perception SLAM

来源：评论

学校读者我要写书评

暂无评论

Pair-VPR: Place-Aware Pre-Training and Contrastive Pair Classification for visual Place Recognition With Vision Transformers

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第4期10卷 4013-4020页

作者： Hausler, Stephen Moghadam, Peyman CSIRO CSIRO Robot Data61 Brisbane Qld 4069 Australia Queensland Univ Technol QUT Sch Elect Engn & Robot Brisbane 4069 Australia

In this work we propose a novel joint training method for visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair classifier can predict whether a given pair of images are from the same place or not. The network only comprises Vision Transformer components for both the encoder and the pair classifier, and both components are trained using their respective class tokens. In existing VPR methods, typically the network is initialized using pre-trained weights from a generic image dataset such as ImageNet. In this work we propose an alternative pre-training strategy, by using Siamese Masked Image Modeling as a pre-training task. We propose a Place-aware image sampling procedure from a collection of large VPR datasets for pre-training our model, to learn visual features tuned specifically for VPR. By re-using the Mask Image Modeling encoder and decoder weights in the second stage of training, Pair-VPR can achieve state-of-the-art VPR performance across five benchmark datasets with a ViT-B encoder, along with further improvements in localization recall with larger encoders.

关键词： visual place recognition Transformers Decoding Training Image reconstruction Computer vision Benchmark testing Image recognition Data models visualization deep learning for visual perception Recognition Localization

来源：评论

学校读者我要写书评

暂无评论

Bayesian NeRF: Quantifying Uncertainty With Volume Density for Neural Implicit Fields

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第3期10卷 2144-2151页

作者： Lee, Sibaek Kang, Kyeongsu Ha, Seongbo Yu, Hyeonwoo Sungkyunkwan Univ Dept Intelligent Robot Suwon 12345 South Korea

We present a Bayesian Neural Radiance Field (NeRF), which explicitly quantifies uncertainty in the volume density by modeling uncertainty in the occupancy, without the need for additional networks, making it particularly suited for challenging observations and uncontrolled image environments. NeRF diverges from traditional geometric methods by providing an enriched scene representation, rendering color and density in 3D space from various viewpoints. However, NeRF encounters limitations in addressing uncertainties solely through geometric structure information, leading to inaccuracies when interpreting scenes with insufficient real-world observations. While previous efforts have relied on auxiliary networks, we propose a series of formulation extensions to NeRF that manage uncertainties in density, both color and density, and occupancy, all without the need for additional networks. In experiments, we show that our method significantly enhances performance on RGB and depth images in the comprehensive dataset. Given that uncertainty modeling aligns well with the inherently uncertain environments of Simultaneous Localization and Mapping (SLAM), we applied our approach to SLAM systems and observed notable improvements in mapping and tracking performance. These results confirm the effectiveness of our Bayesian NeRF approach in quantifying uncertainty based on geometric structure, making it a robust solution for challenging real-world scenarios.

关键词： Uncertainty Neural radiance field Image color analysis Three-dimensional displays Bayes methods Rendering (computer graphics) Estimation Cameras Solid modeling Simultaneous localization and mapping deep learning for visual perception mapping SLAM

来源：评论

学校读者我要写书评

暂无评论

Taxonomy-Aware Continual Semantic Segmentation in Hyperbolic Spaces for Open-World perception

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第2期10卷 1904-1911页

作者： Hindel, Julia Cattaneo, Daniele Valada, Abhinav Univ Freiburg Dept Comp Sci D-79110 Freiburg Germany

Semantic segmentation models are typically trained on a fixed set of classes, limiting their applicability in open-world scenarios. Class-incremental semantic segmentation aims to update models with emerging new classes while preventing catastrophic forgetting of previously learned ones. However, existing methods impose strict rigidity on old classes, reducing their effectiveness in learning new incremental classes. In this work, we propose Taxonomy-Oriented Poincar & eacute;-regularized Incremental-Class Segmentation (TOPICS) that learns feature embeddings in hyperbolic space following explicit taxonomy-tree structures. This supervision provides plasticity for old classes, updating ancestors based on new classes while integrating new classes at fitting positions. Additionally, we maintain implicit class relational constraints on the geometric basis of the Poincar & eacute;ball. This ensures that the latent space can continuously adapt to new constraints while maintaining a robust structure to combat catastrophic forgetting. We also establish eight realistic incremental learning protocols for autonomous driving scenarios, where novel classes can originate from known classes or the background. Extensive evaluations of TOPICS on the Cityscapes and Mapillary Vistas 2.0 benchmarks demonstrate that it achieves state-of-the-art performance.

关键词： Semantic segmentation Semantics Taxonomy Data models Incremental learning Training Rigidity Adaptation models visualization Predictive models Continual learning incremental learning deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

Event-Driven Force Measurement of a Variable-Stiffness Robotic Finger Using Masked Autoencoder Pre-Training

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第6期10卷 5831-5838页

作者： Guo, Qianyu Lu, Yawen Fu, Jiaming Gan, Dongming Purdue Univ Sch Engn Technol W Lafayette IN 47906 USA Purdue Univ Comp Graph Technol Dept W Lafayette IN 47906 USA Univ West Florida Mech Engn Dept Pensacola FL 32514 USA

Force feedback in compliant robotic grippers is essential for precise manipulation tasks but remains challenging because irregular deformation of soft materials renders traditional sensor integration impractical. Event camera has emerged as a powerful alternative to conventional vision sensors through their ability to capture only temporal changes in a scene, thereby significantly reducing data redundancy and processing overhead. In this letter, we introduce a novel vision-based force prediction framework that employs a Mamba-Like architecture to process event camera data in compliant grippers. To validate our approach, we have developed a custom gripper with variable stiffness and created a comprehensive dataset comprising over 9,000 event frames. Our methodology combines self-supervised pre-training for learning rich feature representations with a Mamba-like regression framework to achieve accurate force prediction. The proposed method demonstrates a 0.14 improvement in RMSE when compared to existing Vision Transformer approaches. Through extensive experimental validation-including real-time performance analysis, ablation studies, and generalization tests across various gripper configurations-we demonstrate the framework's effectiveness. Our results indicate robust performance suitable for practical industrial applications, suggesting potential extensions to other compliant robotics applications that require precise force estimation.

关键词： Grippers Cameras Robots Force Force measurement Robot vision systems Fingers Accuracy Sensors Computer vision deep learning for visual perception AI-based methods bioinspired robot learning data sets for robot learning

来源：评论

学校读者我要写书评

暂无评论

LatentBKI: Open-Dictionary Continuous Mapping in visual-Language Latent Spaces With Quantifiable Uncertainty

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第4期10卷 3102-3109页

作者： Wilson, Joey Xu, Ruihan Sun, Yile Ewen, Parker Zhu, Minghan Barton, Kira Ghaffari, Maani Univ Michigan Ann Arbor MI 48109 USA

This letter introduces a novel probabilistic mapping algorithm, LatentBKI, which enables open-vocabulary mapping with quantifiable uncertainty. Traditionally, semantic mapping algorithms focus on a fixed set of semantic categories which limits their applicability for complex robotic tasks. Vision-Language (VL) models have recently emerged as a technique to jointly model language and visual features in a latent space, enabling semantic recognition beyond a predefined, fixed set of semantic classes. LatentBKI recurrently incorporates neural embeddings from VL models into a voxel map with quantifiable uncertainty, leveraging the spatial correlations of nearby observations through Bayesian Kernel Inference (BKI). LatentBKI is evaluated against similar explicit semantic mapping and VL mapping frameworks on the popular Matterport3D and Semantic KITTI data sets, demonstrating that LatentBKI maintains the probabilistic benefits of continuous mapping with the additional benefit of open-dictionary queries. Real-world experiments demonstrate applicability to challenging indoor environments.

关键词： Uncertainty Semantics Robots Kernel Neural networks Bayes methods Probabilistic logic Three-dimensional displays Smoothing methods visualization Mapping semantic scene understanding deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

ConditionNET: learning Preconditions and Effects for Execution Monitoring

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2025年第2期10卷 1337-1344页

作者： Sliwowski, Daniel Lee, Dongheui Tech Univ Wien TU Wien Autonomous Syst Lab A-1040 Vienna Austria Inst Robot & Mechatron DLR German Aerosp Ctr D-82234 Wessling Germany

The introduction of robots into everyday scenarios necessitates algorithms capable of monitoring the execution of tasks. In this letter, we propose ConditionNET, an approach for learning the preconditions and effects of actions in a fully data-driven manner. We develop an efficient vision-language model and introduce additional optimization objectives during training to optimize for consistent feature representations. ConditionNET explicitly models the dependencies between actions, preconditions, and effects, leading to improved performance. We evaluate our model on two robotic datasets, one of which we collected for this letter, containing 406 successful and 138 failed teleoperated demonstrations of a Franka Emika Panda robot performing tasks like pouring and cleaning the counter. We show in our experiments that ConditionNET outperforms all baselines on both anomaly detection and phase prediction tasks. Furthermore, we implement an action monitoring system on a real robot to demonstrate the practical applicability of the learned preconditions and effects. Our results highlight the potential of ConditionNET for enhancing the reliability and adaptability of robots in real-world environments.

关键词： Robot sensing systems Monitoring Feature extraction Hidden Markov models Planning Probabilistic logic Natural languages Image segmentation Anomaly detection Transformers deep learning methods data sets for robot learning deep learning for visual perception

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：