Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact, supporting dynamical predictions, as well as inferences about the abstract properties of the system. Our model takes graphs as input, performs object-and relation-centric reasoning in a way that is analogous to a simulation, and is implemented using deep neural networks. We evaluate its ability to reason about several challenging physical domains: n-body problems, rigid-body collision, and non-rigid dynamics. Our results show it can be trained to accurately simulate the physical trajectories of dozens of objects over thousands of time steps, estimate abstract quantities such as energy, and generalize automatically to systems with different numbers and configurations of objects and relations. Our interaction network implementation is the first general-purpose, learnable physics engine, and a powerful general framework for reasoning about object and relations in a wide variety of complex real-world domains.
translated by 谷歌翻译
Here we present a machine learning framework and model implementation that can learn to simulate a wide variety of challenging physical domains, involving fluids, rigid solids, and deformable materials interacting with one another. Our framework-which we term "Graph Network-based Simulators" (GNS)-represents the state of a physical system with particles, expressed as nodes in a graph, and computes dynamics via learned message-passing. Our results show that our model can generalize from single-timestep predictions with thousands of particles during training, to different initial conditions, thousands of timesteps, and at least an order of magnitude more particles at test time. Our model was robust to hyperparameter choices across various evaluation metrics: the main determinants of long-term performance were the number of message-passing steps, and mitigating the accumulation of error by corrupting the training data with noise. Our GNS framework advances the state-of-the-art in learned physical simulation, and holds promise for solving a wide range of complex forward and inverse problems.
translated by 谷歌翻译
在学识表的迅速推进的地区,几乎所有方法都训练了从输入状态直接预测未来状态的前进模型。然而,许多传统的仿真引擎使用基于约束的方法而不是直接预测。这里我们提出了一种基于约束的学习仿真的框架,其中标量约束函数被实现为神经网络,并且将来的预测被计算为在这些学习的约束下的优化问题的解决方案。我们使用图形神经网络作为约束函数和梯度下降作为约束求解器来实现我们的方法。架构可以通过标准的backprojagation培训。我们在各种具有挑战性的物理领域中测试模型,包括模拟绳索,弹跳球,碰撞不规则形状和飞溅液。我们的模型可实现更好或更具可比性的性能,以获得最佳学习的模拟器。我们模型的一个关键优势是能够在测试时间概括到更多求解器迭代,以提高模拟精度。我们还展示了如何在测试时间内添加手工制定的约束,以满足培训数据中不存在的目标,这是不可能的前进方法。我们的约束框架适用于使用前进学习模拟器的任何设置,并演示了学习的模拟器如何利用额外的归纳偏差以及来自数值方法领域的技术。
translated by 谷歌翻译
虽然牛顿力学的基本规律得到了很好的理解,但是解释了物理场景仍然需要用合适的方程式制造问题并估计相关参数。为了能够利用人工智能技术在这种物理相关的背景下利用近似能力,研究人员已经手工制作了相关状态,然后使用神经网络来学习使用模拟运行作为训练数据的状态转换。遗憾的是,这种方法不适合建模复杂的现实情景,在手动创作相关的状态空间往往是乏味和挑战性的。在这项工作中,我们研究了神经网络是否可以基于视觉数据隐含地学习现实世界机械过程的物理状态,而在内部建模非均匀环境中,并且在该过程中可以实现长期物理推断。我们为此任务开发了经常性的神经网络架构,并且还以不断变化的方差估计的形式表征了结果的不确定性。我们评估我们的设置,以推断在不同形状和方向的碗上的滚珠球运动,以及仅使用图像作为输入的任意高度场。我们在对预测的准确性和情景复杂性方面,我们报告了对现有的基于图像的方法的显着改进;并报告与我们不同的方法,竞争性能与我们不同,承担进入内部物理状态。
translated by 谷歌翻译
Relational reasoning is a central component of generally intelligent behavior, but has proven difficult for neural networks to learn. In this paper we describe how to use Relation Networks (RNs) as a simple plug-and-play module to solve problems that fundamentally hinge on relational reasoning. We tested RN-augmented networks on three tasks: visual question answering using a challenging dataset called CLEVR, on which we achieve state-of-the-art, super-human performance; text-based question answering using the bAbI suite of tasks; and complex reasoning about dynamic physical systems. Then, using a curated dataset called Sort-of-CLEVR we show that powerful convolutional networks do not have a general capacity to solve relational questions, but can gain this capacity when augmented with RNs. Our work shows how a deep learning architecture equipped with an RN module can implicitly discover and learn to reason about entities and their relations.
translated by 谷歌翻译
尽管当前的视觉算法在许多具有挑战性的任务上都表现出色,但尚不清楚他们如何理解现实世界环境的物理动态。在这里,我们介绍了Physion,一种数据集和基准,用于严格评估预测物理场景如何随着时间而发展的能力。我们的数据集具有对各种物理现象的现实模拟,包括刚性和软体体碰撞,稳定的多对象配置,滚动,滑动和弹丸运动,因此比以前的基准提供了更全面的挑战。我们使用Physion来基准一套模型,其体系结构,学习目标,投入输出结构和培训数据各不相同。同时,我们在同一场景上获得了人类预测行为的精确测量,从而使我们能够直接评估任何模型能够近似人类行为的效果。我们发现,学习以对象为中心的表示的视觉算法通常优于那些没有人的表现,但仍未达到人类绩效。另一方面,绘制具有直接访问物理状态信息的神经网络的表现效果更好,并且做出与人类制作的预测更相似。这些结果表明,提取场景的物理表征是在视力算法中实现人类水平和类似人类的物理理解的主要瓶颈。我们已公开发布了所有数据和代码,以促进使用物理以完全可重现的方式对其他模型进行基准测试,从而使对视觉算法的进度进行系统的评估,这些算法像人们一样坚固地了解物理环境。
translated by 谷歌翻译
Simulating rigid collisions among arbitrary shapes is notoriously difficult due to complex geometry and the strong non-linearity of the interactions. While graph neural network (GNN)-based models are effective at learning to simulate complex physical dynamics, such as fluids, cloth and articulated bodies, they have been less effective and efficient on rigid-body physics, except with very simple shapes. Existing methods that model collisions through the meshes' nodes are often inaccurate because they struggle when collisions occur on faces far from nodes. Alternative approaches that represent the geometry densely with many particles are prohibitively expensive for complex shapes. Here we introduce the Face Interaction Graph Network (FIGNet) which extends beyond GNN-based methods, and computes interactions between mesh faces, rather than nodes. Compared to learned node- and particle-based methods, FIGNet is around 4x more accurate in simulating complex shape interactions, while also 8x more computationally efficient on sparse, rigid meshes. Moreover, FIGNet can learn frictional dynamics directly from real-world data, and can be more accurate than analytical solvers given modest amounts of training data. FIGNet represents a key step forward in one of the few remaining physical domains which have seen little competition from learned simulators, and offers allied fields such as robotics, graphics and mechanical design a new tool for simulation and model-based planning.
translated by 谷歌翻译
机器人中的一个重要挑战是了解机器人与由粒状材料组成的可变形地形之间的相互作用。颗粒状流量及其与刚体的互动仍然造成了几个开放的问题。有希望的方向,用于准确,且有效的建模使用的是使用连续体方法。此外,实时物理建模的新方向是利用深度学习。该研究推进了用于对刚性体驱动颗粒流建模的机器学习方法,用于应用于地面工业机器以及空间机器人(重力的效果是一个重要因素的地方)。特别是,该研究考虑了子空间机器学习仿真方法的开发。要生成培训数据集,我们利用我们的高保真连续体方法,材料点法(MPM)。主要成分分析(PCA)用于降低数据的维度。我们表明我们的高维数据的前几个主要组成部分几乎保持了数据的整个方差。培训图形网络模拟器(GNS)以学习底层子空间动态。然后,学习的GNS能够以良好的准确度预测颗粒位置和交互力。更重要的是,PCA在训练和卷展栏中显着提高了GNS的时间和记忆效率。这使得GNS能够使用具有中等VRAM的单个桌面GPU进行培训。这也使GNS实时在大规模3D物理配置(比我们的连续方法快700倍)。
translated by 谷歌翻译
我们介绍了ThreedWorld(TDW),是交互式多模态物理模拟的平台。 TDW能够模拟高保真感官数据和富裕的3D环境中的移动代理和对象之间的物理交互。独特的属性包括:实时近光 - 真实图像渲染;对象和环境库,以及他们定制的例程;有效构建新环境课程的生成程序;高保真音频渲染;各种材料类型的现实物理相互作用,包括布料,液体和可变形物体;可定制的代理体现AI代理商;并支持与VR设备的人类交互。 TDW的API使多个代理能够在模拟中进行交互,并返回一系列表示世界状态的传感器和物理数据。我们在计算机视觉,机器学习和认知科学中的新兴的研究方向上提供了通过TDW的初始实验,包括多模态物理场景理解,物理动态预测,多代理交互,像孩子一样学习的模型,并注意研究人类和神经网络。
translated by 谷歌翻译
Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics. The interplay of components can give rise to complex behavior, which can often be explained using a simple model of the system's constituent parts. In this work, we introduce the neural relational inference (NRI) model: an unsupervised model that learns to infer interactions while simultaneously learning the dynamics purely from observational data. Our model takes the form of a variational auto-encoder, in which the latent code represents the underlying interaction graph and the reconstruction is based on graph neural networks. In experiments on simulated physical systems, we show that our NRI model can accurately recover ground-truth interactions in an unsupervised manner. We further demonstrate that we can find an interpretable structure and predict complex dynamics in real motion capture and sports tracking data.
translated by 谷歌翻译
微弱的物理是计算机视觉和机器人的强大工具,用于了解互动的场景理解和推理。现有方法经常被限于具有预先已知的简单形状或形状的物体。在本文中,我们提出了一种新的方法来具有摩擦触点的可分解物理学,其利用符号距离场(SDF)隐含地表示物理形状。我们的模拟即使涉及的形状为非凸形表示,也支持接触点计算。此外,我们提出了区分对象形状的动力学来利用基于梯度的方法来促进形状优化。在我们的实验中,我们证明我们的方法允许从轨迹和深度图像观察的诸如摩擦系数,质量,力或形状参数的物理参数的基于模型的推断,并且在几个具有挑战性的合成场景和真实图像序列中。
translated by 谷歌翻译
在这项工作中,我们提出了一个端到端的图形网络,其使用可解释的电感偏差来学习粒子基物理学的前进和逆模型。物理知识的神经网络通常通过特定于问题的正则化和损失功能来解决特定问题。这种显式学习偏置网络以学习数据特定模式,并且可能需要在特此限制其Generalizabiliy的丢失功能或神经网络架构的变化。虽然最近的研究已经提出了图形网络来研究前瞻性动态,但它们依赖于粒子特定参数,例如质量等。我们的图形网络通过学习来隐含地偏见,以解决多项任务,从而在任务之间共享表示,以便学习前向动态以及推断未知粒子特定属性的概率分布。我们在一步的下一个状态预测任务上评估了我们的方法,这些任务跨越具有不同粒子交互的不同数据集。我们对相关数据驱动物理学学习方法的比较揭示了我们的模型能够预测至少一种更高的准确度的前向动态。我们还表明,我们的方法能够使用较少的样本的数量令恢复未知物理参数的多模态概率分布。
translated by 谷歌翻译
合并适当的归纳偏差在从数据的学习动态中发挥着关键作用。通过将拉格朗日或哈密顿的动态编码到神经网络架构中,越来越多的工作已经探索了在学习动态中实施节能的方法。这些现有方法基于微分方程,其不允许州中的不连续性,从而限制了一个人可以学习的系统。然而,实际上,大多数物理系统,例如腿机器人和机器人操纵器,涉及联系和碰撞,这在各州引入了不连续性。在本文中,我们介绍了一种可微分的接触型号,可以捕获接触机械:无摩擦/摩擦,以及弹性/无弹性。该模型还可以适应不等式约束,例如关节角度的限制。拟议的联系模式通过允许同时学习联系和系统性质来扩展拉格朗日和哈密顿神经网络的范围。我们在具有不同恢复系数和摩擦系数的一系列具有挑战性的2D和3D物理系统上展示了这一框架。学习的动态可以用作用于下游梯度的优化任务的可分解物理模拟器,例如规划和控制。
translated by 谷歌翻译
Deep learning models, though having achieved great success in many different fields over the past years, are usually data hungry, fail to perform well on unseen samples, and lack of interpretability. Various prior knowledge often exists in the target domain and their use can alleviate the deficiencies with deep learning. To better mimic the behavior of human brains, different advanced methods have been proposed to identify domain knowledge and integrate it into deep models for data-efficient, generalizable, and interpretable deep learning, which we refer to as knowledge-augmented deep learning (KADL). In this survey, we define the concept of KADL, and introduce its three major tasks, i.e., knowledge identification, knowledge representation, and knowledge integration. Different from existing surveys that are focused on a specific type of knowledge, we provide a broad and complete taxonomy of domain knowledge and its representations. Based on our taxonomy, we provide a systematic review of existing techniques, different from existing works that survey integration approaches agnostic to taxonomy of knowledge. This survey subsumes existing works and offers a bird's-eye view of research in the general area of knowledge-augmented deep learning. The thorough and critical reviews of numerous papers help not only understand current progresses but also identify future directions for the research on knowledge-augmented deep learning.
translated by 谷歌翻译
学习动态是机器学习(ML)的许多重要应用的核心,例如机器人和自主驾驶。在这些设置中,ML算法通常需要推理使用高维观察的物理系统,例如图像,而不访问底层状态。最近,已经提出了几种方法将从经典机制的前沿集成到ML模型中,以解决图像的物理推理的挑战。在这项工作中,我们清醒了这些模型的当前功能。为此,我们介绍一套由17个数据集组成的套件,该数据集基于具有呈现各种动态的物理系统的视觉观测。我们对几种强大的基线进行了彻底的和详细比较了物理启发方法的主要类别。虽然包含物理前沿的模型通常可以学习具有所需特性的潜在空间,但我们的结果表明这些方法无法显着提高标准技术。尽管如此,我们发现使用连续和时间可逆动力学的使用效益所有课程的模型。
translated by 谷歌翻译
基于粒子的系统提供了一种灵活而统一的方法,可以模拟具有复杂动力学的物理系统。大多数现有的基于粒子系统的数据驱动的模拟器采用图形神经网络(GNN)作为网络骨架,因为粒子及其相互作用可以由图节点和图形边缘自然表示。但是,虽然基于粒子的系统通常包含数百千个颗粒,但由于粒子相互作用的数量增加,粒子相互作用的显式建模不可避免地会导致显着的计算开销。因此,在本文中,我们提出了一种基于变压器的新型方法,称为具有隐式边缘(TIE)的变压器,以无边缘方式捕获粒子相互作用的丰富语义。领带的核心思想是将涉及涉及配对粒子相互作用的计算分散到每个颗粒更新中。这是通过调整自我发项式模块以类似于GNN中图表的更新公式来实现的。为了提高领带的概括能力,我们进一步修改了可学习的特定材料的抽象粒子,以将全球材料的语义与本地粒子语义分开。我们评估了不同复杂性和材料不同领域的模型。与现有的基于GNN的方法相比,没有铃铛和哨子,TIE可以在所有这些领域中实现卓越的性能和概括。代码和模型可在https://github.com/ftbabi/tie_eccv2022.git上找到。
translated by 谷歌翻译
Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn, and how they learn it. Specifically, we argue that these machines should (a) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (b) ground learning in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned; and (c) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes towards these goals that can combine the strengths of recent neural network advances with more structured cognitive models.
translated by 谷歌翻译
我们提出了一种从基于隐式对象编码器,神经辐射字段(NERFS)和图神经网络的图像观测值中学习组成多对象动力学模型的方法。由于其强大的3D先验,NERF已成为代表场景的流行选择。但是,大多数NERF方法都在单个场景上进行了训练,以全球模型代表整个场景,从而对新型场景进行概括,其中包含不同数量的对象,具有挑战性。取而代之的是,我们提出了一个以对象为中心的自动编码器框架,该框架将场景的多个视图映射到一组分别表示每个对象的潜在向量。潜在矢量参数化可以从中重建场景的单个nerf。基于那些潜在向量,我们在潜在空间中训练图形神经网络动力学模型,以实现动力学预测的组成性。我们方法的一个关键特征是,潜在向量被迫通过NERF解码器编码3D信息,这使我们能够在学习动力学模型中纳入结构先验,从而使长期预测与多个基线相比更加稳定。模拟和现实世界的实验表明,我们的方法可以建模和学习构图场景的动态,包括刚性和可变形对象。视频:https://dannydriess.github.io/compnerfdyn/
translated by 谷歌翻译
学习包括不同对象之间接触的动态系统的物理结构化表示是机器人技术中基于学习的方法的重要问题。黑盒神经网络可以学会大致表示不连续的动态,但是它们通常需要大量数据,并且在预测更长的时间范围时通常会遭受病理行为。在这项工作中,我们使用深层神经网络和微分方程之间的连接来设计一个深网架构家族,以表示对象之间的接触动态。我们表明,这些网络可以从传统上难以实现黑盒方法和最近启发的神经网络的设置中的嘈杂的观察结果中以数据效率的方式学习不连续的联系事件。我们的结果表明,一种理想化的触摸反馈形式(由生物系统严重依赖)是使这一学习问题可以解决的关键组成部分。加上通过网络体系结构引入的电感偏差,我们的技术可以从观测值中准确学习接触动力学。
translated by 谷歌翻译
准确地对现实世界进行建模接触行为,对于现有的刚体物理模拟器而言,近刚毛的材料仍然是一个巨大的挑战。本文介绍了一个数据增强的接触模型,该模型将分析解决方案与观察到的数据结合在一起,以预测3D接触脉冲,这可能会导致刚体在各个方向上弹跳,滑动或旋转。我们的方法通过从观察到的数据中学习接触行为来增强标准库仑接触模型的表现力,同时尽可能保留基本的接触约束。例如,对分类器进行了训练,以近似静态摩擦和动态摩擦之间的过渡,而在碰撞过程中的非渗透约束在分析中执行。我们的方法计算整个刚体的触点的汇总效果,而不是分别预测每个接触点的接触力,而保持相同的模拟速度,而与接触点的数量增加了详细的几何形状。补充视频:https://shorturl.at/eilwx关键字:物理模拟算法,动态学习,联系人学习
translated by 谷歌翻译