We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped into three themes: (1) visual navigation, (2) rearrangement, and (3) embodied vision-and-language. We discuss the dominant datasets within each theme, evaluation metrics for the challenges, and the performance of state-of-the-art models. We highlight commonalities between top approaches to the challenges and identify potential future directions for Embodied AI research.
translated by 谷歌翻译
自主代理可以在新环境中导航而不构建明确的地图吗?对于PointGoal Navigation的任务(“转到$ \ delta x $,$ \ delta y $'),在理想化的设置(否RGB -D和驱动噪声,完美的GPS+Compass)下,答案是一个明确的“是” - 由任务无形组件(CNNS和RNN)组成的无地图神经模型接受了大规模增强学习训练,在标准数据集(Gibson)上取得了100%的成功。但是,对于PointNav在现实环境中(RGB-D和致动噪声,没有GPS+Compass),这是一个悬而未决的问题。我们在本文中解决了一个。该任务的最强成绩是成功的71.7%。首先,我们确定了性能下降的主要原因:GPS+指南针的缺失。带有RGB-D传感和致动噪声的完美GPS+指南针的代理商取得了99.8%的成功(Gibson-V2 Val)。这表明(解释模因)强大的视觉探子仪是我们对逼真的PointNav所需的全部。如果我们能够实现这一目标,我们可以忽略感应和致动噪声。作为我们的操作假设,我们扩展了数据集和模型大小,并开发了无人批准的数据启发技术来训练模型以进行视觉探测。我们在栖息地现实的PointNAV挑战方面的最新状态从71%降低到94%的成功(+23,31%相对)和53%至74%的SPL(+21,40%相对)。虽然我们的方法不饱和或“解决”该数据集,但这种强大的改进与有希望的零射击SIM2REAL转移(到Locobot)相结合提供了与假设一致的证据,即即使在现实环境中,显式映射也不是必需的。 。
translated by 谷歌翻译
我们介绍了栖息地2.0(H2.0),这是一个模拟平台,用于培训交互式3D环境和复杂物理的场景中的虚拟机器人。我们为体现的AI堆栈 - 数据,仿真和基准任务做出了全面的贡献。具体来说,我们提出:(i)复制:一个由艺术家的,带注释的,可重新配置的3D公寓(匹配真实空间)与铰接对象(例如可以打开/关闭的橱柜和抽屉); (ii)H2.0:一个高性能物理学的3D模拟器,其速度超过8-GPU节点上的每秒25,000个模拟步骤(实时850x实时),代表先前工作的100倍加速;和(iii)家庭助理基准(HAB):一套辅助机器人(整理房屋,准备杂货,设置餐桌)的一套常见任务,以测试一系列移动操作功能。这些大规模的工程贡献使我们能够系统地比较长期结构化任务中的大规模加固学习(RL)和经典的感官平面操作(SPA)管道,并重点是对新对象,容器和布局的概括。 。我们发现(1)与层次结构相比,(1)平面RL政策在HAB上挣扎; (2)具有独立技能的层次结构遭受“交接问题”的困扰,(3)水疗管道比RL政策更脆。
translated by 谷歌翻译
在这项工作中,我们提出了一种用于图像目标导航的内存调格方法。早期的尝试,包括基于RL的基于RL的方法和基于SLAM的方法的概括性能差,或者在姿势/深度传感器上稳定稳定。我们的方法基于一个基于注意力的端到端模型,该模型利用情节记忆来学习导航。首先,我们以自我监督的方式训练一个国家安置的网络,然后将其嵌入以前访问的状态中的代理商的记忆中。我们的导航政策通过注意机制利用了此信息。我们通过广泛的评估来验证我们的方法,并表明我们的模型在具有挑战性的吉布森数据集上建立了新的最新技术。此外,与相关工作形成鲜明对比的是,我们仅凭RGB输入就实现了这种令人印象深刻的性能,而无需访问其他信息,例如位置或深度。
translated by 谷歌翻译
We present Habitat, a platform for research in embodied artificial intelligence (AI). Habitat enables training embodied agents (virtual robots) in highly efficient photorealistic 3D simulation. Specifically, Habitat consists of: (i) Habitat-Sim: a flexible, high-performance 3D simulator with configurable agents, sensors, and generic 3D dataset handling. Habitat-Sim is fast -when rendering a scene from Matterport3D, it achieves several thousand frames per second (fps) running single-threaded, and can reach over 10,000 fps multi-process on a single GPU. (ii) Habitat-API: a modular high-level library for end-toend development of embodied AI algorithms -defining tasks (e.g. navigation, instruction following, question answering), configuring, training, and benchmarking embodied agents.These large-scale engineering contributions enable us to answer scientific questions requiring experiments that were till now impracticable or 'merely' impractical. Specifically, in the context of point-goal navigation: (1) we revisit the comparison between learning and SLAM approaches from two recent works [20,16] and find evidence for the opposite conclusion -that learning outperforms SLAM if scaled to an order of magnitude more experience than previous investigations, and (2) we conduct the first cross-dataset generalization experiments {train, test} × {Matterport3D, Gibson} for multiple sensors {blind, RGB, RGBD, D} and find that only agents with depth (D) sensors generalize across datasets. We hope that our open-source platform and these findings will advance research in embodied AI.
translated by 谷歌翻译
The monograph summarizes and analyzes the current state of development of computer and mathematical simulation and modeling, the automation of management processes, the use of information technologies in education, the design of information systems and software complexes, the development of computer telecommunication networks and technologies most areas that are united by the term Industry 4.0
translated by 谷歌翻译
We introduce ensembles of stochastic neural networks to approximate the Bayesian posterior, combining stochastic methods such as dropout with deep ensembles. The stochastic ensembles are formulated as families of distributions and trained to approximate the Bayesian posterior with variational inference. We implement stochastic ensembles based on Monte Carlo dropout, DropConnect and a novel non-parametric version of dropout and evaluate them on a toy problem and CIFAR image classification. For CIFAR, the stochastic ensembles are quantitatively compared to published Hamiltonian Monte Carlo results for a ResNet-20 architecture. We also test the quality of the posteriors directly against Hamiltonian Monte Carlo simulations in a simplified toy model. Our results show that in a number of settings, stochastic ensembles provide more accurate posterior estimates than regular deep ensembles.
translated by 谷歌翻译
TensorFlow GNN(TF-GNN)是张量曲线的图形神经网络的可扩展库。它是从自下而上设计的,以支持当今信息生态系统中发生的丰富的异质图数据。Google的许多生产模型都使用TF-GNN,最近已作为开源项目发布。在本文中,我们描述了TF-GNN数据模型,其KERAS建模API以及相关功能,例如图形采样,分布式训练和加速器支持。
translated by 谷歌翻译
这项研究致力于解决该问题,以确定使用人工智能系统的建筑管理人员的专业自适应能力。它提议了完全连接的馈送前向前神经网络体系结构,并执行了经验建模以创建数据集。人工智能系统的模型允许在执行专业领域的多价分类过程中评估完全连接的前馈神经网络中的过程。已经为机器学习模型的培训过程开发了一种方法,该方法反映了人工智能系统的组件之间的内部连接,使其可以从培训数据中学习。为了训练神经网络,使用了35个输入参数和29个输出参数的数据集;集合中的数据量为936个数据线。神经网络训练的比例分别为10%和90%。这项研究的结果可用于进一步提高成功实现专业实现所需的知识和技能。
translated by 谷歌翻译
败血症是一种威胁生命的患有器官功能障碍的疾病,是全球死亡和重症疾病的主要原因。急诊科分类过程中败血症的准确检测将允许尽早开始实验室分析,抗生素给药和其他败血症治疗方案。这项研究的目的是确定是否可以将EHR数据与最新的机器学习算法(Kate Sepsis)和临床自然语言处理一起提取和合成,以产生准确的脓毒症模型,并将Kate Sepsis与现有的败血症筛查方案进行比较爵士和QSOFA。使用来自16家参与医院的分类数据的患者遇到的患者遭遇开发了机器学习模型(Kate Sepsis)。凯特败血症,SIRS,标准筛查(具有感染源的SIRS)和QSOFA在三个设置中进行了测试。队列A是对单个站点1的医疗记录的回顾性分析。同类B是对位点1的前瞻性分析1.同伴C是对站点1的回顾性分析,并有15个地点。在所有队列中,凯特败血症的AUC为0.94-0.963,TPR为73-74.87%和3.76-7.17%FPR。标准筛选显示AUC为0.682-0.726,TPR为39.39-51.19%和2.9-6.02%FPR。 QSOFA协议的AUC为0.544-0.56,TPR为10.52-13.18%和1.22-1.68%FPR。对于严重的败血症,在所有队列中,凯特败血症的AUC为0.935-0.972,TPR为70-82.26%和4.64-8.62%FPR。对于败血性休克,在所有队列中,凯特败血症的AUC为0.96-0.981,TPR为85.71-89.66%和4.85-8.8%FPR。 SIRS,标准筛选和QSOFA表现出严重败血症和败血性休克检测的低AUC和TPR。凯特败血症在分类中提供的败血症检测性能比常用的筛查方案更好。
translated by 谷歌翻译