检索结果-内蒙古大学图书馆

High-Speed Detector for Low-Powered Devices in Aerial Grasping

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第5期9卷 4623-4630页

作者： Kumar, Ashish Behera, Laxmidhar Indian Inst Technol IIT EE Kanpur 208016 India

Autonomous aerial harvesting is a highly complex problem because it requires numerous interdisciplinary algorithms to be executed on mini low-powered computing devices. Object detection is one such algorithm that is compute-hungry. In this context, we make the following contributions: (i) Fast Fruit Detector (FFD), a resource-efficient, single-stage, and postprocessing-free object detector based on our novel latent object representation (LOR) module, query assignment, and prediction strategy. FFD achieves 100 FPS @ FP 32 precision on the latest 10 W NVIDIA Jetson-NX embedded device while co-existing with other time-critical sub-systems such as control, grasping, SLAM, a major achievement of this work, (ii) a method to generate vast amounts of training data without exhaustive manual labelling of fruit images since they consist of a large number of instances, which increases the labelling cost and time, and (iii) an open-source fruit detection dataset having plenty of very small-sized instances that are difficult to detect. Our exhaustive evaluations on our and MinneApple dataset show that FFD, being only a single-scale detector, is more accurate than many representative detectors, e.g. FFD is better than single-scale Faster-RCNN by 10.7 AP, multi-scale Faster-RCNN by 2.3 AP, and better than latest single-scale YOLO-v 8 by 8 AP and multi-scale YOLO-v 8 by 0.3 while being considerably faster.

关键词： Aerial systems: applications agricultural automation deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

State Estimation and Belief Space Planning Under Epistemic Uncertainty for learning-Based perception Systems

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第6期9卷 5118-5125页

作者： Nagami, Keiko Schwager, Mac Stanford Univ Dept Aeronaut & Astronaut Stanford CA 94305 USA

learning-based models for robot perception are known to suffer from two distinct sources of error: aleatoric and epistemic. Aleatoric uncertainty arises from inherently noisy training data and is easily quantified from residual errors during training. Conversely, epistemic uncertainty arises from a lack of training data, appearing in out-of-distribution operating regimes, and is difficult to quantify. Most existing state estimation methods handle aleatoric uncertainty through a learned noise model, but ignore epistemic uncertainty. In this work, we propose: (i) an epistemic Kalman filter (EpiKF) to incorporate epistemic uncertainty into state estimation with learned perception models, and (ii) an epistemic belief space planner (EpiBSP) that builds on the EpiKF to plan trajectories to avoid areas of high epistemic and aleatoric uncertainty. Our key insight is to train a generative model that predicts measurements from states, "inverting" the learned perception model that predicts states from measurements. We compose these two models in a sampling scheme to give a well-calibrated online estimate of combined epistemic and aleatoric uncertainty. We demonstrate our method in a vision-based drone racing scenario, and show superior performance to existing methods that treat measurement noise covariance as a learned output of the perception model.

关键词： Uncertainty Planning Measurement uncertainty Trajectory Neural networks Training data Training Aerial systems: perception and autonomy planning under uncertainty deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

AnyLoc: Towards Universal visual Place Recognition

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第2期9卷 1286-1293页

作者： Keetha, Nikhil Mishra, Avneesh Karhade, Jay Jatavallabhula, Krishna Murthy Scherer, Sebastian Krishna, Madhava Garg, Sourav Carnegie Mellon Univ Robot Inst Pittsburgh PA 15213 USA Int Inst Informat Technol Hyderabad 500032 India MIT Cambridge MA 02139 USA Univ Adelaide Australian Inst Machine Learning Adelaide SA 5000 Australia

visual Place Recognition (VPR) is vital for robot localization. To date, the most performant VPR approaches are environment- and task-specific: while they exhibit strong performance in structured environments (predominantly urban driving), their performance degrades severely in unstructured environments, rendering most approaches brittle to robust real-world deployment. In this work, we develop a universal solution to VPR - a technique that works across a broad range of structured and unstructured environments (urban, outdoors, indoors, aerial, underwater, and subterranean environments) without any re-training or finetuning. We demonstrate that general-purpose feature representations derived from off-the-shelf self-supervised models with no VPR-specific training are the right substrate upon which to build such a universal VPR solution. Combining these derived features with unsupervised feature aggregation enables our suite of methods, AnyLoc, to achieve up to 4x significantly higher performance than existing approaches. We further obtain a 6% improvement in performance by characterizing the semantic properties of these features, uncovering unique domains which encapsulate datasets from similar environments. Our detailed experiments and analysis lay a foundation for building VPR solutions that may be deployed anywhere, anytime, and across anyview.

关键词： Feature extraction Training visualization Task analysis Vocabulary Semantics Robustness Localization recognition deep learning for visual perception vision-based navigation

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Topological Localization for MAVs

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第2期9卷 1158-1165页

作者： Felicioni, Simone Rizzo, Biagio Maria Tortorici, Claudio Costante, Gabriele Univ Perugia Dept Engn I-06125 Perugia Italy Technol Innovat Inst Abu Dhabi U Arab Emirates

Vision-based topological localization is recently emerging as a promising alternative to metric pose estimation techniques in robotic navigation systems. Contrarily to the latter, which suffer from a quick degradation of their performance under non-ideal conditions (e.g., scenes with poor illumination and low amount of textures), topological localization trades off precise metric positioning with a more robust and higher-level location representation. State-of-the-art works in this direction, however, often neglect the spatiotemporal relationships between poses that are naturally induced by robotic navigation. Furthermore, these techniques are nearly unexplored for autonomous flying platforms. Inspired by these considerations, in this work, we propose a vision-based topological localization approach designed for Micro Aerial Vehicles (MAVs) applications. Our strategy exploits the framework of graph recurrent neural networks to model the spatial and temporal dependencies and estimate the location of the robot with respect to a topological graph representing the environment. We demonstrate with experiments on different sets of scenarios, including scenes that considerably differ from those used in the training phase, that our approach is able to outperform state-of-the-art place recognition baselines.

关键词： Aerial systems perception and autonomy deep learning for visual perception localization

来源：评论

学校读者我要写书评

暂无评论

Adaptive learning for Hybrid visual Odometry

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第8期9卷 7341-7348页

作者： Liu, Ziming Malis, Ezio Martinet, Philippe INRIA ACENTAURI F-06560 Sophia Antipolis France Bosch Res Shanghai 200335 Peoples R China

Hybrid visual odometry methods achieve state-of-the-art performance by fusing both data-based deep learning networks and model-based localization approaches. However, these methods also suffer from deep learning domain gap problems, which leads to an accuracy drop of the hybrid visual odometry approach when new type of data is considered. This letter is the first to explore a practical solution to this problem. Indeed, the deep learning network in the hybrid visual odometry predicts the stereo disparity with fixed searching space. However, the disparity distribution is unbalanced in stereo images acquired in different environments. We propose an adaptive network structure to overcome this problem. Secondly, the model-based localization module has a robust performance by online optimizing the camera pose in test data, which motivates us to introduce test-time training machine learning method for improving the data-based part of the hybrid visual odometry model.

关键词： deep learning for visual perception visual learning computer vision for transportation deep learning for visual perception visual learning computer vision for transportation

来源：评论

学校读者我要写书评

暂无评论

UADA3D: Unsupervised Adversarial Domain Adaptation for 3D Object Detection With Sparse LiDAR and Large Domain Gaps

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第12期9卷 11210-11217页

作者： Wozniak, Maciej K. Hansson, Mattias Thiel, Marko Jensfelt, Patric KTH Royal Inst Technol Div Robot Percept & Learning S-11428 Stockholm Sweden Hamburg Univ Technol Inst Tech Logist D-21073 Hamburg Germany

In this study, we address a gap in existing unsupervised domain adaptation approaches on LiDAR-based 3D object detection, which have predominantly concentrated on adapting between established, high-density autonomous driving datasets. We focus on sparser point clouds, capturing scenarios from different perspectives: not just from vehicles on the road but also from mobile robots on sidewalks, which encounter significantly different environmental conditions and sensor configurations. We introduce Unsupervised Adversarial Domain Adaptation for 3D Object Detection (UADA3D). UADA3D does not depend on pre-trained source models or teacher-student architectures. Instead, it uses an adversarial approach to directly learn domain-invariant features. We demonstrate its efficacy in various adaptation scenarios, showing significant improvements in both self-driving car and mobile robot domains.

关键词： Feature extraction Three-dimensional displays Laser radar Object detection Robot sensing systems Adaptation models Point cloud compression Solid modeling Training Mobile robots deep learning for visual perception object detection segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

learning Semantic Traversability With Egocentric Video and Automated Annotation Strategy

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第11期9卷 10423-10430页

作者： Kim, Yunho Lee, Jeong Hyun Lee, Choongin Mun, Juhyeok Youm, Donghoon Park, Jeongsoo Hwangbo, Jemin Korea Adv Inst Sci & Technol Robot & Artificial Intelligence Lab Daejeon 34141 South Korea Neuromeka Seoul 04782 South Korea

For reliable autonomous robot navigation in urban settings, the robot must have the ability to identify semantically traversable terrains in the image based on the semantic understanding of the scene. This reasoning ability is based on semantic traversability, which is frequently achieved using semantic segmentation models fine-tuned on the testing domain. This fine-tuning process often involves manual data collection with the target robot and annotation by human labelers which is prohibitively expensive and unscalable. In this work, we present an effective methodology for training a semantic traversability estimator using egocentric videos and an automated annotation process. Egocentric videos are collected from a camera mounted on a pedestrian's chest. The dataset for training the semantic traversability estimator is then automatically generated by extracting semantically traversable regions in each video frame using a recent foundation model in image segmentation and its prompting technique. Extensive experiments with videos taken across several countries and cities, covering diverse urban scenarios, demonstrate the high scalability and generalizability of the proposed annotation method. Furthermore, performance analysis and real-world deployment for autonomous robot navigation showcase that the trained semantic traversability estimator is highly accurate, able to handle diverse camera viewpoints, computationally light, and real-world applicable.

关键词： deep learning for visual perception semantic scene understanding vision-based navigation vision-based navigation vision-based navigation

来源：评论

学校读者我要写书评

暂无评论

FGDSNet: A Lightweight Hand Gesture Recognition Network for Human Robot Interaction

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第4期9卷 3076-3083页

作者： Zhou, Guoyu Cui, Zhenchao Qi, Jing Hebei Univ Sch Cyber Secur & Comp Baoding 071000 Peoples R China

Computer vision-based gesture recognition methods play a significant role in robot visual gesture interaction. since of low accuracy leading by insuffcient feature representation and fusion, the existing gesture segmentation and recognition methods fail to meet the requirements of practical applications. To address these issues, a lightweight two-stage end-to-end gesture recognition network called Fusing Gate Dual Stages Network (FGDSNet) is proposed. This network adopts a dual-branch network structure in the segmentation stage. Existing dual-branch network models often directly fuse detailed features and semantic features, which leads to detailed information being obscured by blurry semantic information. Additionally, there are redundant issues in the feature maps at different levels during the network inference process. Therefore, we embed Cosine Similarity-KL Divergence Attention Module (CoSKLAM) and Gate Filtering Module (GFM) between the local detail branch and the contextual semantic branch. The role of these two modules is to facilitate the fusion of local and global features during the feature extraction process and filter out redundant information. Finally, the segmentation result and original gesture image are used as inputs for the recognition network to predict gesture categories. The relevant experiments show that the proposed network performs well in both gesture segmentation and gesture recognition, while also having real-time inference speed and a smaller parameter size.

关键词： Gesture recognition Semantics Image segmentation Feature extraction Robots Real-time systems Object segmentation deep learning for visual perception human-robot collaboration hand gesture segmentation and recognition

来源：评论

学校读者我要写书评

暂无评论

AerialVL: A Dataset, Baseline and Algorithm Framework for Aerial-Based visual Localization With Reference Map

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第10期9卷 8210-8217页

作者： He, Mengfan Chen, Chao Liu, Jiacheng Li, Chunyu Lyu, Xu Huang, Guoquan Meng, Ziyang Tsinghua Univ Dept Precis Instrument Beijing 100084 Peoples R China Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China Unmanned Aerial Vehicle Lab Beijing 100012 Peoples R China Univ Delaware Dept Mech Engn Dept Comp & Informat Sci Newark DE 19716 USA

visual localization plays an essential role in the autonomous flight of Unmanned Aerial Vehicles (UAVs) especially for the Global Navigation Satellite System (GNSS) denied environments. Existing aerial-based visual localization methods mainly focus on eliminating image variance between database map and captured frames. However, these is a lack of public dataset and baseline for method comparisons, which impedes the development of aerial-based visual localization. To address this issue, we construct AerialVL, a large-scale dataset, which is collected using UAV flying at different altitudes, along various routes, and during diverse time periods. AerialVL consists of 11 image sequences covering approximately 70 km of trajectory and includes a reference satellite image database corresponding to the flight area. Leveraging AerialVL, we perform thorough evaluations on various mainstream solutions designed for aerial-based visual localization for the first time. This evaluation encompasses visual place recognition, visual alignment localization and visual odometry, serving as comparison baselines. Furthermore, we present a general aerial-based visual localization framework, which unifies various methods and integrates them into a modular architecture. We note that across all flight trajectories, the proposed framework achieves higher localization accuracy and robustness against the existing methods.

关键词： Location awareness visualization Trajectory Satellite images Global navigation satellite system Autonomous aerial vehicles Cameras deep learning for visual perception localization recognition vision-based navigation

来源：评论

学校读者我要写书评

暂无评论

A Sim-to-Real Instance Segmentation Framework for Densely Stacked Cartons

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2024年第6期9卷 5775-5782页

作者： Wang, Xu Li, Junliang Zheng, Wenli Luo, Huanliang Wang, Faping Chen, Yongquan Huang, Rui Chinese Univ Hong Kong Shenzhen Inst Artificial Intelligence & Robot Soc Shenzhen 518172 Peoples R China Dapeng Customs Peoples Republ China Shenzhen 518083 Peoples R China Shenzhen Haixing Intelligent Driving Technol Co Lt Shenzhen 518110 Guangdong Peoples R China

Robotic picking systems in automated logistics require accurate segmentation and localization of densely stacked cartons. However, the lack of comprehensive and diverse datasets for this task poses a significant challenge. Furthermore, existing instance segmentation methods struggle to meet the accuracy requirements due to the unique characteristics of cartons, including their large quantity, small spatial gaps, similar postures, and complex textures. To address these issues, this letter proposes a sim-to-real instance segmentation framework specifically designed for densely stacked cartons. Synthetic data of densely stacked cartons is generated using an automated simulation pipeline, resulting in the Densely Stacked Object Dataset (DSOD) with 40 000 data samples and 1 209 951 individually segmented cartons in various environmental settings. The instance segmentation network employs gated fully fusion and disentangled non-local modules to prioritize salient boundaries, improving segmentation accuracy. Experimental evaluation on both the DSOD and an existing real-world carton dataset demonstrates that our method outperforms state-of-the-art techniques, achieving an impressive performance of 85.2 on AP50 and 78.7 on AP75. These findings highlight the effectiveness of our sim-to-real framework for accurately segmenting and localizing densely stacked cartons.

关键词： Instance segmentation Pipelines Synthetic data Location awareness Grasping Task analysis Stacking Object detection segmentation and categorization deep learning for visual perception data sets for robotic vision

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：