我们提出了一种使用图像增强的自我监督训练方法,用于学习视图的视觉描述符。与通常需要复杂数据集的现有作品(例如注册的RGBD序列)不同,我们在无序的一组RGB图像上训练。这允许从单个相机视图(例如,在带有安装式摄像机的现有机器人单元格中学习)学习。我们使用数据增强创建合成视图和密集的像素对应关系。尽管数据记录和设置要求更简单,但我们发现我们的描述符与现有方法具有竞争力。我们表明,对合成对应的培训提供了各种相机视图的描述符的一致性。我们将训练与来自多种视图的几何对应关系进行比较,并提供消融研究。我们还使用从固定式摄像机中学到的描述符显示了一个机器人箱进行挑选实验,以定义掌握偏好。
translated by 谷歌翻译
我们为对密集物体网(DON)的稳健训练(DON)提出了一个框架,重点是多对象机器人操纵方案。 DON是一种获取密集的,视图的对象描述符的流行方法,可用于机器人操纵中的多种下游任务,例如,姿势估算,控制状态表示控制等。在唱歌对象上,在实例特定的多对象应用程序上的结果有限。此外,训练需要复杂的数据收集管道,包括每个对象的3D重建和掩盖注释。在本文中,我们通过简化的数据收集和培训制度进一步提高了DON的功效,从而始终如一地产生更高的精度,并能够对数据要求较少的关键点进行强有力的跟踪。特别是,我们专注于使用多对象数据而不是奇异的对象进行培训,并结合精心挑选的增强方案。我们还针对原始PixelWise配方提出了一种替代损失公式,该配方提供了更好的结果,并且对超参数较少敏感。最后,我们在现实世界的机器人抓握任务上展示了我们提出的框架的鲁棒性和准确性。
translated by 谷歌翻译
当代掌握检测方法采用深度学习,实现传感器和物体模型不确定性的鲁棒性。这两个主导的方法设计了掌握质量评分或基于锚的掌握识别网络。本文通过将其视为图像空间中的关键点检测来掌握掌握检测的不同方法。深网络检测每个掌握候选者作为一对关键点,可转换为掌握代表= {x,y,w,{\ theta}} t,而不是转角点的三态或四重奏。通过将关键点分组成对来降低检测难度提高性能。为了促进捕获关键点之间的依赖关系,将非本地模块结合到网络设计中。基于离散和连续定向预测的最终过滤策略消除了错误的对应关系,并进一步提高了掌握检测性能。此处提出的方法GKNET在康奈尔和伸缩的提花数据集上的精度和速度之间实现了良好的平衡(在41.67和23.26 fps的96.9%和98.39%)之间。操纵器上的后续实验使用4种类型的抓取实验来评估GKNet,反映不同滋扰的速度:静态抓握,动态抓握,在各种相机角度抓住,夹住。 GKNet优于静态和动态掌握实验中的参考基线,同时表现出变化的相机观点和中度杂波的稳健性。结果证实了掌握关键点是深度掌握网络的有效输出表示的假设,为预期的滋扰因素提供鲁棒性。
translated by 谷歌翻译
我们呈现神经描述符字段(NDFS),对象表示,其通过类别级别描述符在对象和目标(例如用于悬挂的机器人夹具或用于悬挂的机架)之间进行编码和相对姿势。我们使用此表示进行对象操作,在这里,在给定任务演示时,我们要在同一类别中对新对象实例重复相同的任务。我们建议通过搜索(通过优化)来实现这一目标,为演示中观察到的描述符匹配的姿势。 NDFS通过不依赖于专家标记的关键点的3D自动编码任务,方便地以自我监督的方式培训。此外,NDFS是SE(3) - 保证在所有可能的3D对象翻译和旋转中推广的性能。我们展示了在仿真和真正的机器人上的少数(5-10)示范中的操纵任务的学习。我们的性能遍历两个对象实例和6-DOF对象姿势,并且显着优于最近依赖于2D描述符的基线。项目网站:https://yilundu.github.io/ndf/。
translated by 谷歌翻译
密集对象跟踪,能够通过像素级精度本地化特定的对象点,是一个重要的计算机视觉任务,具有多种机器人的下游应用程序。现有方法在单个前向通行证中计算密集的键盘嵌入,这意味着模型培训以一次性跟踪所有内容,或者将它们的全部容量分配给稀疏预定义的点,交易一般性以获得准确性。在本文中,我们基于观察到给定时间的相关点数通常相对较少,例如,探索中间地面。掌握目标对象的点。我们的主要贡献是一种新颖的架构,灵感来自少量任务适应,这允许一个稀疏样式的网络在嵌入点嵌入的关键点嵌入时的条件。我们的中央发现是,这种方法提供了密集嵌入模型的一般性,同时提供准确性更加接近稀疏关键点方法。我们呈现了说明此容量与准确性权衡的结果,并使用真正的机器人挑选任务展示将转移到新对象实例(在课程中)的能力。
translated by 谷歌翻译
As the basis for prehensile manipulation, it is vital to enable robots to grasp as robustly as humans. In daily manipulation, our grasping system is prompt, accurate, flexible and continuous across spatial and temporal domains. Few existing methods cover all these properties for robot grasping. In this paper, we propose a new methodology for grasp perception to enable robots these abilities. Specifically, we develop a dense supervision strategy with real perception and analytic labels in the spatial-temporal domain. Additional awareness of objects' center-of-mass is incorporated into the learning process to help improve grasping stability. Utilization of grasp correspondence across observations enables dynamic grasp tracking. Our model, AnyGrasp, can generate accurate, full-DoF, dense and temporally-smooth grasp poses efficiently, and works robustly against large depth sensing noise. Embedded with AnyGrasp, we achieve a 93.3% success rate when clearing bins with over 300 unseen objects, which is comparable with human subjects under controlled conditions. Over 900 MPPH is reported on a single-arm system. For dynamic grasping, we demonstrate catching swimming robot fish in the water.
translated by 谷歌翻译
我们提出了一种称为DPODV2(密集姿势对象检测器)的三个阶段6 DOF对象检测方法,该方法依赖于致密的对应关系。我们将2D对象检测器与密集的对应关系网络和多视图姿势细化方法相结合,以估计完整的6 DOF姿势。与通常仅限于单眼RGB图像的其他深度学习方法不同,我们提出了一个统一的深度学习网络,允许使用不同的成像方式(RGB或DEPTH)。此外,我们提出了一种基于可区分渲染的新型姿势改进方法。主要概念是在多个视图中比较预测并渲染对应关系,以获得与所有视图中预测的对应关系一致的姿势。我们提出的方法对受控设置中的不同数据方式和培训数据类型进行了严格的评估。主要结论是,RGB在对应性估计中表现出色,而如果有良好的3D-3D对应关系,则深度有助于姿势精度。自然,他们的组合可以实现总体最佳性能。我们进行广泛的评估和消融研究,以分析和验证几个具有挑战性的数据集的结果。 DPODV2在所有这些方面都取得了出色的成果,同时仍然保持快速和可扩展性,独立于使用的数据模式和培训数据的类型
translated by 谷歌翻译
6多机器人抓钩是一个持久但未解决的问题。最近的方法利用强3D网络从深度传感器中提取几何抓握表示形式,表明对公共物体的准确性卓越,但对光度化挑战性物体(例如,透明或反射材料中的物体)进行不满意。瓶颈在于这些物体的表面由于光吸收或折射而无法反射准确的深度。在本文中,与利用不准确的深度数据相反,我们提出了第一个称为MonograspNet的只有RGB的6-DOF握把管道,该管道使用稳定的2D特征同时处理任意对象抓握,并克服由光学上具有挑战性挑战的对象引起的问题。 MonograspNet利用关键点热图和正常地图来恢复由我们的新型表示形式表示的6-DOF抓握姿势,该表示的2D键盘具有相应的深度,握把方向,抓握宽度和角度。在真实场景中进行的广泛实验表明,我们的方法可以通过在抓住光学方面挑战的对象方面抓住大量对象并超过基于深度的竞争者的竞争成果。为了进一步刺激机器人的操纵研究,我们还注释并开源一个多视图和多场景现实世界抓地数据集,其中包含120个具有20m精确握把标签的混合光度复杂性对象。
translated by 谷歌翻译
实时机器人掌握,支持随后的精确反对操作任务,是高级高级自治系统的优先目标。然而,尚未找到这样一种可以用时间效率进行充分准确的掌握的算法。本文提出了一种新的方法,其具有2阶段方法,它使用深神经网络结合快速的2D对象识别,以及基于点对特征框架的随后的精确和快速的6D姿态估计来形成实时3D对象识别和抓握解决方案能够多对象类场景。所提出的解决方案有可能在实时应用上稳健地进行,需要效率和准确性。为了验证我们的方法,我们进行了广泛且彻底的实验,涉及我们自己的数据集的费力准备。实验结果表明,该方法在5CM5DEG度量标准中的精度97.37%,平均距离度量分数99.37%。实验结果显示了通过使用该方法的总体62%的相对改善(5cm5deg度量)和52.48%(平均距离度量)。此外,姿势估计执行也显示出运行时间的平均改善47.6%。最后,为了说明系统在实时操作中的整体效率,进行了一个拾取和放置的机器人实验,并显示了90%的准确度的令人信服的成功率。此实验视频可在https://sites.google.com/view/dl-ppf6dpose/上获得。
translated by 谷歌翻译
视觉感知任务通常需要大量的标记数据,包括3D姿势和图像空间分割掩码。创建此类培训数据集的过程可能很难或耗时,可以扩展到一般使用的功效。考虑对刚性对象的姿势估计的任务。在大型公共数据集中接受培训时,基于神经网络的深层方法表现出良好的性能。但是,将这些网络调整为其他新颖对象,或针对不同环境的现有模型进行微调,需要大量的时间投资才能产生新标记的实例。为此,我们提出了ProgressLabeller作为一种方法,以更有效地以可扩展的方式从彩色图像序列中生成大量的6D姿势训练数据。 ProgressLabeller还旨在支持透明或半透明的对象,以深度密集重建的先前方法将失败。我们通过快速创建一个超过1M样品的数据集来证明ProgressLabeller的有效性,我们将其微调一个最先进的姿势估计网络,以显着提高下游机器人的抓地力。 ProgressLabeller是https://github.com/huijiezh/progresslabeller的开放源代码。
translated by 谷歌翻译
Estimating 6D poses of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images of an object against the input image can produce accurate results. In this work, we propose a novel deep neural network for 6D pose matching named DeepIM. Given an initial pose estimation, our network is able to iteratively refine the pose by matching the rendered image against the observed image. The network is trained to predict a relative pose transformation using a disentangled representation of 3D location and 3D orientation and an iterative training process. Experiments on two commonly used benchmarks for 6D pose estimation demonstrate that DeepIM achieves large improvements over stateof-the-art methods. We furthermore show that DeepIM is able to match previously unseen objects.
translated by 谷歌翻译
形状通知如何将对象掌握,无论是如何以及如何。因此,本文介绍了一种基于分割的架构,用于将用深度摄像机进行分解为多个基本形状的对象,以及用于机器人抓握的后处理管道。分段采用深度网络,称为PS-CNN,在具有6个类的原始形状和使用模拟引擎生成的合成数据上培训。每个原始形状都设计有参数化掌握家族,允许管道识别每个形状区域的多个掌握候选者。掌握是排序的排名,选择用于执行的第一个可行的。对于无任务掌握单个对象,该方法达到94.2%的成功率将其放置在顶部执行掌握方法中,与自上而下和SE(3)基础相比。涉及变量观点和杂波的其他测试展示了设置的鲁棒性。对于面向任务的掌握,PS-CNN实现了93.0%的成功率。总体而言,结果支持该假设,即在抓地管道内明确地编码形状原语应该提高掌握性能,包括无任务和任务相关的掌握预测。
translated by 谷歌翻译
尽管提取了通过手工制作和基于学习的描述符实现的本地特征的进步,但它们仍然受到不符合非刚性转换的不变性的限制。在本文中,我们提出了一种计算来自静止图像的特征的新方法,该特征对于非刚性变形稳健,以避免匹配可变形表面和物体的问题。我们的变形感知当地描述符,命名优惠,利用极性采样和空间变压器翘曲,以提供旋转,尺度和图像变形的不变性。我们通过将等距非刚性变形应用于模拟环境中的对象作为指导来提供高度辨别的本地特征来培训模型架构端到端。该实验表明,我们的方法优于静止图像中的实际和现实合成可变形对象的不同数据集中的最先进的手工制作,基于学习的图像和RGB-D描述符。描述符的源代码和培训模型在https://www.verlab.dcc.ufmg.br/descriptors/neUrips2021上公开可用。
translated by 谷歌翻译
Being able to grasp objects is a fundamental component of most robotic manipulation systems. In this paper, we present a new approach to simultaneously reconstruct a mesh and a dense grasp quality map of an object from a depth image. At the core of our approach is a novel camera-centric object representation called the "object shell" which is composed of an observed "entry image" and a predicted "exit image". We present an image-to-image residual ConvNet architecture in which the object shell and a grasp-quality map are predicted as separate output channels. The main advantage of the shell representation and the corresponding neural network architecture, ShellGrasp-Net, is that the input-output pixel correspondences in the shell representation are explicitly represented in the architecture. We show that this coupling yields superior generalization capabilities for object reconstruction and accurate grasp quality estimation implicitly considering the object geometry. Our approach yields an efficient dense grasp quality map and an object geometry estimate in a single forward pass. Both of these outputs can be used in a wide range of robotic manipulation applications. With rigorous experimental validation, both in simulation and on a real setup, we show that our shell-based method can be used to generate precise grasps and the associated grasp quality with over 90% accuracy. Diverse grasps computed on shell reconstructions allow the robot to select and execute grasps in cluttered scenes with more than 93% success rate.
translated by 谷歌翻译
A hallmark of the deep learning era for computer vision is the successful use of large-scale labeled datasets to train feature representations for tasks ranging from object recognition and semantic segmentation to optical flow estimation and novel view synthesis of 3D scenes. In this work, we aim to learn dense discriminative object representations for low-shot category recognition without requiring any category labels. To this end, we propose Deep Object Patch Encodings (DOPE), which can be trained from multiple views of object instances without any category or semantic object part labels. To train DOPE, we assume access to sparse depths, foreground masks and known cameras, to obtain pixel-level correspondences between views of an object, and use this to formulate a self-supervised learning task to learn discriminative object patches. We find that DOPE can directly be used for low-shot classification of novel categories using local-part matching, and is competitive with and outperforms supervised and self-supervised learning baselines. Code and data available at https://github.com/rehg-lab/dope_selfsup.
translated by 谷歌翻译
The accurate detection and grasping of transparent objects are challenging but of significance to robots. Here, a visual-tactile fusion framework for transparent object grasping under complex backgrounds and variant light conditions is proposed, including the grasping position detection, tactile calibration, and visual-tactile fusion based classification. First, a multi-scene synthetic grasping dataset generation method with a Gaussian distribution based data annotation is proposed. Besides, a novel grasping network named TGCNN is proposed for grasping position detection, showing good results in both synthetic and real scenes. In tactile calibration, inspired by human grasping, a fully convolutional network based tactile feature extraction method and a central location based adaptive grasping strategy are designed, improving the success rate by 36.7% compared to direct grasping. Furthermore, a visual-tactile fusion method is proposed for transparent objects classification, which improves the classification accuracy by 34%. The proposed framework synergizes the advantages of vision and touch, and greatly improves the grasping efficiency of transparent objects.
translated by 谷歌翻译
在许多机器人应用中,要执行已知,刚体对象及其随后的抓握的6多-DOF姿势估计的环境设置几乎保持不变,甚至可能是机器人事先知道的。在本文中,我们将此问题称为特定实例的姿势估计:只有在有限的一组熟悉的情况下,该机器人将以高度准确性估算姿势。场景中的微小变化,包括照明条件和背景外观的变化,是可以接受的,但没有预期的改变。为此,我们提出了一种方法,可以快速训练和部署管道,以估算单个RGB图像的对象的连续6-DOF姿势。关键的想法是利用已知的相机姿势和刚性的身体几何形状部分自动化大型标记数据集的生成。然后,数据集以及足够的域随机化来监督深度神经网络的培训,以预测语义关键。在实验上,我们证明了我们提出的方法的便利性和有效性,以准确估计物体姿势,仅需要少量的手动注释才能进行训练。
translated by 谷歌翻译
We introduce MegaPose, a method to estimate the 6D pose of novel objects, that is, objects unseen during training. At inference time, the method only assumes knowledge of (i) a region of interest displaying the object in the image and (ii) a CAD model of the observed object. The contributions of this work are threefold. First, we present a 6D pose refiner based on a render&compare strategy which can be applied to novel objects. The shape and coordinate system of the novel object are provided as inputs to the network by rendering multiple synthetic views of the object's CAD model. Second, we introduce a novel approach for coarse pose estimation which leverages a network trained to classify whether the pose error between a synthetic rendering and an observed image of the same object can be corrected by the refiner. Third, we introduce a large-scale synthetic dataset of photorealistic images of thousands of objects with diverse visual and shape properties and show that this diversity is crucial to obtain good generalization performance on novel objects. We train our approach on this large synthetic dataset and apply it without retraining to hundreds of novel objects in real images from several pose estimation benchmarks. Our approach achieves state-of-the-art performance on the ModelNet and YCB-Video datasets. An extensive evaluation on the 7 core datasets of the BOP challenge demonstrates that our approach achieves performance competitive with existing approaches that require access to the target objects during training. Code, dataset and trained models are available on the project page: https://megapose6d.github.io/.
translated by 谷歌翻译
对图像分类任务的对比学习成功的鼓励,我们为3D手姿势估计的结构化回归任务提出了一种新的自我监督方法。对比学习利用未标记的数据来通过损失制定来使用未标记的数据,以鼓励学习的特征表示在任何图像转换下都是不变的。对于3D手姿势估计,它也希望具有不变性地与诸如颜色抖动的外观变换。但是,该任务需要在仿射和转换之类的转换下的标准性。为了解决这个问题,我们提出了一种对比的对比目标,并在3D手姿势估计的背景下展示其有效性。我们通过实验研究了不变性和对比的对比目标的影响,并表明学习的等待特征导致3D手姿势估计的任务的更好表示。此外,我们显示具有足够深度的标准Evenet,在额外的未标记数据上培训,在弗雷手中获得高达14.5%的提高,因此在没有任何任务的专用架构的情况下实现最先进的性能。 https://ait.ethz.ch/projects/2021/peclr/使用代码和模型
translated by 谷歌翻译
We describe a learning-based approach to handeye coordination for robotic grasping from monocular images. To learn hand-eye coordination for grasping, we trained a large convolutional neural network to predict the probability that task-space motion of the gripper will result in successful grasps, using only monocular camera images and independently of camera calibration or the current robot pose. This requires the network to observe the spatial relationship between the gripper and objects in the scene, thus learning hand-eye coordination. We then use this network to servo the gripper in real time to achieve successful grasps. To train our network, we collected over 800,000 grasp attempts over the course of two months, using between 6 and 14 robotic manipulators at any given time, with differences in camera placement and hardware. Our experimental evaluation demonstrates that our method achieves effective real-time control, can successfully grasp novel objects, and corrects mistakes by continuous servoing.
translated by 谷歌翻译