检索结果-内蒙古大学图书馆

Head and Eye Egocentric Gesture Recognition for Human-Robot Interaction Using Eyewear Cameras

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第3期7卷 7067-7074页

作者： Marina-Miranda, Javier Javier Traver, V Univ Jaume 1 E-12071 Castellon de La Plana Spain HP Inc Barcelona 08174 Spain Univ Jaume 1 Inst New Imaging Technol E-12071 Castellon de La Plana Spain

Non-verbal communication plays a particularly important role in a wide range of scenarios in Human-Robot Interaction (HRI). Accordingly, this work addresses the problem of human gesture recognition. In particular, we focus on head and eye gestures, and adopt an egocentric (first-person) perspective using eyewear cameras. We argue that this egocentric view may offer a number of conceptual and technical benefits over scene- or robot-centric perspectives. A motion-based recognition approach is proposed, which operates at two temporal granularities. Locally, frame-to-frame homographies are estimated with a convolutional neural network (CNN). The output of this CNN is input to a long short-term memory (LSTM) to capture longer-term temporal visual relationships, which are relevant to characterize gestures. Regarding the configuration of the network architecture, one particularly interesting finding is that using the output of aninternal layer of the homography CNN increases the recognition rate with respect to using the homography matrix itself. While this work focuses on action recognition, and no robot or user study has been conducted yet, the system has been designed to meet real-time constraints. The encouraging results suggest that the proposed egocentric perspective is viable, and this proofof-concept work provides novel and useful contributions to the exciting area of HRI.

关键词： Gesture posture and facial expressions deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

Template-Based Category-Agnostic Instance Detection for Robotic Manipulation

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第4期7卷 12451-12458页

作者： Hu, Zhongxu Tan, Runjia Zhou, Yanxin Woon, Junyang Lv, Chen Nanyang Technol Univ Sch Mech & Aerosp Engn Singapore 637460 Singapore Nanyang Technol Univ Continental NTU Corp Lab Singapore 637460 Singapore Continental Automot Singapore Pte Ltd Singapore 339780 Singapore

An intelligent robotic system is one of the key pillars of a smart factory that requires flexibility to handle a variety of tasks. perception is a key enabling technology for robots. Most existing object detection studies have mainly focused on category-specific objects and have achieved impressive performance. However, robotic systems, particularly in industrial scenarios, typically interact with many category-agnostic objects, which the robot must detect instantly without pre-training. Therefore, in this study, we proposed a template-based detection and segmentation approach, which incorporated a multi-level correlation model and a similarity-refine module, for handling the category-agnostic instance. The proposed approach was then validated and demonstrated in an interactive and adaptive robotic application scenario designed for the typical pick-and-place task. Among them, the picking scan path and location were instructed through human guidance with hand tracking. The neural rendering technology was also introduced to render novel views of the template. The proposed approach was evaluated using a benchmark and verified through a real demonstration.

关键词： Computer vision for automation deep learning for visual perception human detection and tracking object detection segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

learning-Based Distortion Correction and Feature Detection for High Precision and Robust Camera Calibration

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第4期7卷 10470-10477页

作者： Zhang, Yesheng Zhao, Xu Qian, Dahong Shanghai Jiao Tong Univ Sch Biomed Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Inst Med Robot Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai 200240 Peoples R China

Camera calibration is a crucial technique which significantly influences the performance of many robotic systems. Robustness and high precision have always been the pursuit of diverse calibration methods. State-of-the-art calibration techniques, however, still suffer from inexact corner detection, radial lens distortion and unstable parameter estimation. Therefore, in this paper, we improve the precision and robustness of calibration by widening these bottlenecks. In particular, effective distortion correction is performed by a learning-based method. Then, accurate sub-pixel feature location is achieved by the combination of robust learning detection, exact refinement and complete post-processing. To obtain stable parameter estimation, an image-level RANSAC-based calibration procedure is proposed. Ultimately, we assemble these methods into a novel and practical calibration framework. Compared with state-of-art methods, experiment results on both real and synthetic datasets under noise, bad lighting and distortion manifest the better robustness and higher precision of the proposed framework.

关键词： Calibration and identification deep learning for visual perception visual learning

来源：评论

学校读者我要写书评

暂无评论

A Planted Clique Perspective on Hypothesis Pruning

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 5167-5174页

作者： Lin, Muyuan Murali, Varun Karaman, Sertac MIT Lab Informat & Decis Syst Cambridge MA 02139 USA

Hypothesis pruning is an important prerequisite while working with outlier-contaminated data in many computer vision problems. However, the underlying random data structures are barely explored in the literature, limiting designing efficient algorithms. To this end, we provide a novel graph-theoretic perspective on hypothesis pruning exploiting invariant structures of data. We introduce the planted clique model, a central object in computational statistics, to investigate the information-theoretical and computational limits of the hypothesis pruning problem. In addition, we propose an inductive learning framework for finding hidden cliques that learns heuristics on synthetic graphs with planted cliques and generalizes to real vision problems. We present competitive experimental results with large runtime improvement on synthetic and widely used vision datasets to show its efficacy.

关键词： deep learning for visual perception aerial systems perception and autonomy perception for grasping and manipulation

来源：评论

学校读者我要写书评

暂无评论

Uncertainty for Identifying Open-Set Errors in visual Object Detection

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第1期7卷 215-222页

作者： Miller, Dimity Sunderhauf, Niko Milford, Michael Dayoub, Feras Queensland Univ Technol QUT Brisbane Qld 4000 Australia CSIRO Robot & Autonomous Syst Grp Pullenvale 4069 Australia

Deployed into an open world, object detectors are prone to open-set errors, false positive detections of object classes not present in the training *** propose GMM-Det, a real-time method for extracting epistemic uncertainty from object detectors to identify and reject open-set errors. GMM-Det trains the detector to produce a structured logit space that is modelled with class-specific Gaussian Mixture Models. At test time, open-set errors are identified by their low log-probability under all Gaussian Mixture Models. We test two common detector architectures, Faster R-CNN and RetinaNet, across three varied datasets spanning robotics and computer vision. Our results show that GMM-Det consistently outperforms existing uncertainty techniques for identifying and rejecting open-set detections, especially at the low-error-rate operating point required for safety-critical applications. GMM-Det maintains object detection performance, and introduces only minimal computational overhead. We also introduce a methodology for converting existing object detection datasets into specific open-set datasets to evaluate open-set performance in object detection.

关键词： Object detection segmentation and categorization deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

Fast and Robust Registration of Partially Overlapping Point Clouds

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 1502-1509页

作者： Arnold, Eduardo Mozaffari, Sajjad Dianati, Mehrdad Univ Warwick WMG Coventry CV47AL W Midlands England

Real-time registration of partially overlapping point clouds has emerging applications in cooperative perception for autonomous vehicles and multi-agent SLAM. The relative translation between point clouds in these applications is higher than in traditional SLAM and odometry applications, which challenges the identification of correspondences and a successful registration. In this paper, we propose a novel registration method for partially overlapping point clouds where correspondences are learned using an efficient point-wise feature encoder, and refined using a graph-based attention network. This attention network exploits geometrical relationships between key points to improve the matching in point clouds with low overlap. At inference time, the relative pose transformation is obtained by robustly fitting the correspondences through sample consensus. The evaluation is performed on the KITTI dataset and a novel synthetic dataset including low-overlapping point clouds with displacements of up to 30 m. The proposed method achieves on-par performance with state-of-the-art methods on the KITTI dataset, and outperforms existing methods for low overlapping point clouds. Additionally, the proposed method achieves significantly faster inference times, as low as 410 ms, between 5 and 35 times faster than competing methods. Our code and dataset are available at https://***/eduardohenriquearnold/fastreg.

关键词： Mapping sensor fusion multi-robot systems 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

Vision-Based Sensing for Electrically-Driven Soft Actuators

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第4期7卷 11509-11516页

作者： Zhang, Annan Truby, Ryan L. Chin, Lillian Li, Shuguang Rus, Daniela MIT MIT Comp Sci & Artificial Intelligence Lab CSAIL 77 Massachusetts Ave Cambridge MA 02139 USA Northwestern Univ Dept Mat Sci & Engn Evanston IL 60208 USA Northwestern Univ Dept Mech Engn Evanston IL 60208 USA Tsinghua Univ Dept Mech Engn Beijing 100084 Peoples R China

Developing reliable control strategies in soft robotics requires advances in soft robot perception. However, current soft robotic sensors pose many performance limitations, and available materials and manufacturing techniques complicate soft sensorized robot design. To address these long-standing needs, we introduce a method for using vision to sensorize robust, electrically-driven soft robotic actuators constructed from a new class of architected materials. Specifically, we use cameras positioned within the hollow interiors of handed shearing auxetic (HSA) actuators to record deformation during motion. We train a convolutional neural network (CNN) that maps the visual feedback to the actuator's tip pose. Our model provides predictions with sub-millimeter accuracy from only six minutes of training data, while remaining lightweight with an inference time of 18 milliseconds per frame. We also develop a model that additionally predicts the horizontal tip force acting on the actuator and generalizes to previously unseen forces. Finally, we demonstrate the viability of our sensorization strategy for contact-rich applications by training a CNN that predicts the tip pose accurately during tactile interactions. Overall, our methods present a reliable vision-based approach for designing sensorized soft robots built from electrically-actuated, architected materials.

关键词： deep learning for visual perception force and tactile sensing modeling control and learning for soft robots perception for grasping and manipulation soft sensors and actuators

来源：评论

学校读者我要写书评

暂无评论

iCaps: Iterative Category-Level Object Pose and Shape Estimation

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 1784-1791页

作者： Deng, Xinke Geng, Junyi Bretl, Timothy Xiang, Yu Fox, Dieter Univ Illinois Coordinated Sci Lab Urbana IL 61801 USA Carnegie Mellon Univ Robot Inst Pittsburgh PA 15213 USA Univ Texas Dallas Dept Comp Sci Richardson TX 75080 USA Univ Washington Dept Comp Sci & Engn Seattle WA 98195 USA NVIDIA Seattle WA 98195 USA

This letter proposes a category-level 6D object pose and shape estimation approach iCaps, which allows tracking 6D poses of unseen objects in a category and estimating their 3D shapes. We develop a category-level auto-encoder network using depth images as input, where feature embeddings from the auto-encoder encode poses of objects in a category. The auto-encoder can be used in a particle filter framework to estimate and track 6D poses of objects in a category. By exploiting an implicit shape representation based on signed distance functions, we build a LatentNet to estimate a latent representation of the 3D shape given the estimated pose of an object. Then the estimated pose and shape can be used to update each other in an iterative way. Our category-level 6D object pose and shape estimation pipeline only requires 2D detection and segmentation for initialization. We evaluate our approach on a publicly available dataset and demonstrate its effectiveness. In particular, our method achieves comparably high accuracy on shape estimation.

关键词： RGB-D perception deep learning for visual perception perception for grasping and manipulation category-level 6D pose estimation object shape estimation

来源：评论

学校读者我要写书评

暂无评论

Scalable Scene Flow From Point Clouds in the Real World

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 1589-1596页

作者： Jund, Philipp Sweeney, Chris Abdo, Nichola Chen, Zhifeng Shlens, Jonathon Google Brain Mountain View CA 94043 USA Waymo LLC Mountain View CA 94043 USA

Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ 3D point cloud data from consecutive LiDAR scans, although such approaches have been limited by the small size of real-world, annotated LiDAR data. In this work, we introduce a new largescale dataset for scene flow estimation derived from corresponding tracked 3D objects, which is similar to 1, 000x larger than previous real-world datasets in terms of the number of annotated frames. We demonstrate how previous works were bounded by the amount of real LiDAR data available, suggesting that larger datasets are required to achieve state-of-the-art predictive performance. Furthermore, we show how previous heuristics such as down-sampling heavily degrade performance, motivating a new class of models that are tractable on the full point cloud. To address this issue, we introduce the FastFlow3D architecture which provides real time inference on the full point cloud. Additionally, we design human-interpretablemetrics that better capture realworld aspects by accounting for ego-motion and providing breakdowns per object type. We hope that this dataset may provide new opportunities for developing real world scene flow systems.

关键词： deep learning for visual perception data sets for robot learning

来源：评论

学校读者我要写书评

暂无评论

GA-Nav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第3期7卷 8138-8145页

作者： Guan, Tianrui Kothandaraman, Divya Chandra, Rohan Sathyamoorthy, Adarsh Jagan Weerakoon, Kasun Manocha, Dinesh Univ Maryland Dept Comp Sci College Pk MD 20742 USA Univ Maryland Dept Elect & Comp Engn College Pk MD 20742 USA

We propose GA-Nav, a novel group-wise attention mechanism to identify safe and navigable regions in unstructured environments from RGB images. Our group-wise attention method extracts multi-scale features from each type of terrain independently and classifies terrains based on their navigability levels using coarse-grained semantic segmentation. Our novel loss can be embedded within any backbone network to explicitly focus on the different groups' features, at a low spatial resolution. Our design leads to efficient inference while maintaining a high level of accuracy compared to existing SOTA methods. Our extensive evaluations on the RUGD and RELLIS-3D datasets shows that GA-Nav achieves the state-of-the-art performance on RUGD and RELLIS-3D datasets. We interface GA-Nav with a deep reinforcement learning-based navigation algorithm and highlight its benefits in terms of navigation in real-world unstructured terrains. We integrate our GA-Nav-based navigation algorithm with ClearPath Jackal and Husky robots, and observe an improvement in terms of navigation success rate and better trajectory selections.

关键词： Vision-based navigation AI-enabled robotics deep learning for visual perception AI-based methods deep learning methods

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：