许多数值优化技术的收敛性对提供给求解器的初始猜测高度敏感。我们提出了一种基于张量方法的方法,以初始化靠近全局Optima的现有优化求解器。该方法仅使用成本函数的定义,不需要访问任何良好解决方案的数据库。我们首先将成本函数(这是任务参数和优化变量的函数)转换为概率密度函数。与将任务参数设置为常数的现有方法不同,我们将它们视为另一组随机变量,并使用替代概率模型近似任务参数的关节概率分布和优化变量。对于给定的任务,我们就给定的任务参数从条件分布中生成样本,并将其用作优化求解器的初始化。由于调节和来自任意密度函数的调节和采样具有挑战性,因此我们使用张量列车分解来获得替代概率模型,我们可以从中有效地获得条件模型和样品。该方法可以为给定任务产生来自不同模式的多个解决方案。我们首先通过将其应用于各种具有挑战性的基准函数来评估该方法以进行数值优化,这些功能很难使用基于梯度的优化求解器以幼稚的初始化来求解,这表明所提出的方法可以生成靠近全局优化的样品,并且来自多种模式。 。然后,我们通过将所提出的方法应用于7-DOF操纵器来证明框架的通用性及其与机器人技术的相关性。
translated by 谷歌翻译
在本文中,我们关注将基于能量的模型(EBM)作为运动优化的指导先验的问题。 EBM是一组神经网络,可以用合适的能量函数参数为参数的GIBBS分布来表示表达概率密度分布。由于其隐含性,它们可以轻松地作为优化因素或运动优化问题中的初始采样分布整合在一起,从而使它们成为良好的候选者,以将数据驱动的先验集成在运动优化问题中。在这项工作中,我们提出了一组所需的建模和算法选择,以使EBMS适应运动优化。我们调查了将其他正规化器在学习EBM中的好处,以将它们与基于梯度的优化器一起使用,并提供一组EBM架构,以学习用于操纵任务的可通用分布。我们提出了多种情况,可以将EBM集成以进行运动优化,并评估学到的EBM的性能,以指导模拟和真实机器人实验的指导先验。
translated by 谷歌翻译
将机器人放置在受控条件外,需要多功能的运动表示,使机器人能够学习新任务并使其适应环境变化。在工作区中引入障碍或额外机器人的位置,由于故障或运动范围限制导致的关节范围的修改是典型的案例,适应能力在安全地执行机器人任务的关键作用。已经提出了代表适应性运动技能的概率动态(PROMP),其被建模为轨迹的高斯分布。这些都是在分析讲道的,可以从少数演示中学习。然而,原始PROMP制定和随后的方法都仅为特定运动适应问题提供解决方案,例如障碍避免,以及普遍的,统一的适应概率方法缺失。在本文中,我们开发了一种用于调整PROMP的通用概率框架。我们统一以前的适应技术,例如,各种类型的避避,通过一个框架,互相避免,在一个框架中,并将它们结合起来解决复杂的机器人问题。另外,我们推导了新颖的适应技术,例如时间上未结合的通量和互相避免。我们制定适应作为约束优化问题,在那里我们最小化适应的分布与原始原始的分布之间的kullback-leibler发散,而我们限制了与不希望的轨迹相关的概率质量为低电平。我们展示了我们在双机器人手臂设置中的模拟平面机器人武器和7-DOF法兰卡 - Emika机器人的若干适应问题的方法。
translated by 谷歌翻译
解决逆运动学问题是针对清晰机器人的运动计划,控制和校准的基本挑战。这些机器人的运动学模型通常通过关节角度进行参数化,从而在机器人构型和最终效果姿势之间产生复杂的映射。或者,可以使用机器人附加点之间的不变距离来表示运动学模型和任务约束。在本文中,我们将基于距离的逆运动学的等效性和大量铰接式机器人和任务约束的距离几何问题进行形式化。与以前的方法不同,我们使用距离几何形状和低级别矩阵完成之间的连接来通过局部优化完成部分欧几里得距离矩阵来找到逆运动学解决方案。此外,我们用固定级革兰氏矩阵的Riemannian歧管来参数欧几里得距离矩阵的空间,从而使我们能够利用各种成熟的Riemannian优化方法。最后,我们表明,绑定的平滑性可用于生成知情的初始化,而无需大量的计算开销,从而改善收敛性。我们证明,我们的逆运动求解器比传统技术获得更高的成功率,并且在涉及许多工作区约束的问题上大大优于它们。
translated by 谷歌翻译
我们提出了一种基于有效的量化张量列表表示和广义最大矩阵音量原理的组合进行优化的新过程。我们证明了新的张量火车优化器(TTOPT)方法在各种任务中的适用性,从最小化多维功能到增强学习。我们的算法与流行的基于进化的方法进行了比较,并以函数评估或执行时间的数量(通常是大幅度的余量)优于它们。
translated by 谷歌翻译
工业机器人操纵器(例如柯机)的应用可能需要在具有静态和非静态障碍物组合的环境中有效的在线运动计划。当可用的计算时间受到限制或无法完全产生解决方案时,现有的通用计划方法通常会产生较差的质量解决方案。我们提出了一个新的运动计划框架,旨在在用户定义的任务空间中运行,而不是机器人的工作空间,该框架有意将工作空间一般性交易,以计划和执行时间效率。我们的框架自动构建在线查询的轨迹库,类似于利用离线计算的以前方法。重要的是,我们的方法还提供了轨迹长度上有限的次级优势保证。关键的想法是建立称为$ \ epsilon $ -Gromov-Hausdorff近似值的近似异构体,以便在任务空间附近的点也很接近配置空间。这些边界关系进一步意味着可以平稳地串联轨迹,这使我们的框架能够解决批次查询方案,目的是找到最小长度的轨迹顺序,这些轨迹访问一组无序的目标。我们通过几种运动型配置评估了模拟框架,包括安装在移动基础上的操纵器。结果表明,我们的方法可实现可行的实时应用,并为扩展其功能提供了有趣的机会。
translated by 谷歌翻译
在粗糙的地形上的动态运动需要准确的脚部放置,避免碰撞以及系统的动态不足的计划。在存在不完美且常常不完整的感知信息的情况下,可靠地优化此类动作和互动是具有挑战性的。我们提出了一个完整的感知,计划和控制管道,可以实时优化机器人所有自由度的动作。为了减轻地形所带来的数值挑战,凸出不平等约束的顺序被提取为立足性可行性的局部近似值,并嵌入到在线模型预测控制器中。每个高程映射预先计算了步骤性分类,平面分割和签名的距离场,以最大程度地减少优化过程中的计算工作。多次射击,实时迭代和基于滤波器的线路搜索的组合用于可靠地以高速率解决该法式问题。我们在模拟中的间隙,斜率和踏上石头的情况下验证了所提出的方法,并在Anymal四倍的平台上进行实验,从而实现了最新的动态攀登。
translated by 谷歌翻译
快速,可靠地找到准确的逆运动学(IK)解决方案仍然是机器人操纵的挑战性问题。现有的数值求解器广泛适用,但依赖于本地搜索技术来管理高度非关键目标函数。最近,基于学习的方法已显示出有望作为生成快速准确的IK结果的一种手段。可以轻松地将学习的求解器与端到端系统中的其他学习算法集成在一起。但是,基于学习的方法具有致命的脚跟:每个感兴趣的机器人都需要一个专门的模型,必须从头开始训练。为了解决这一关键缺点,我们研究了一种新颖的距离几何机器人表示,并与图形结构相结合,使我们能够利用图形神经网络(GNNS)的灵活性。我们使用这种方法来训练第一个学到的生成图形逆运动学(GGIK)求解器,它至关重要的是,“机器人 - 敏捷” - 单个模型能够为各种不同的机器人提供IK解决方案。此外,GGIK的生成性质使求解器可以同时生产大量不同的解决方案,并与最小的额外计算时间同行,使其适用于诸如基于采样的运动计划之类的应用。最后,GGIK可以通过提供可靠的初始化来补充本地IK求解器。这些优势以及使用与任务相关的先验并通过新数据不断改进的能力表明,GGIK有可能成为灵活的,基于学习的机器人操作系统的关键组成部分。
translated by 谷歌翻译
反向运动学(IK)是找到满足一个或多个末端效应器的位置或姿势的限制的机器人联合配置的问题。对于具有冗余自由度的机器人,通常存在无限,不透露的解决方案。当通过工作空间中的障碍施加碰撞限制时,IK问题进一步复杂。通常,不存在产生可行配置的闭合表达,促使使用数值解决方案方法。然而,这些方法依赖于局部优化非凸起问题,通常需要准确的初始化或许多重新初始化来收敛到有效的解决方案。在这项工作中,我们首先将复杂的工作空间约束制定逆运动学,作为凸的可行性问题,其低级可行点提供精确的IK解决方案。然后,我们呈现\ texttt {cidgik}(距离 - 几何反向运动学的凸迭代),这是一种解决这种可行性问题的算法,其具有旨在鼓励低秩最小化的半导体级程序的序列。我们的问题制定优雅地统一机器人的配置空间和工作空间约束:内在机器人几何形状和避免避免都表示为简单的线性矩阵方程和不等式。我们对各种流行的操纵器模型的实验结果比传统的非线性优化的方法更快,更准确的会聚,特别是在具有许多障碍的环境中。
translated by 谷歌翻译
逆运动学(IK)解决了从笛卡尔空间到机器人臂的关节配置空间的映射问题。它在计算机图形,蛋白质结构预测和机器人技术等领域具有广泛的应用。随着人工神经网络(NNS)的巨大进步,许多研究人员最近转向了以数据为导向的方法来解决IK问题。不幸的是,NNS因繁殖度(DOFS)的机器人臂而变得不足。这是因为这样的臂可能具有多个角度解决方案以达到相同的所需姿势,而典型的NNS仅实现一对一的映射功能,这仅将一个一致的输出与给定输入相关联。为了培训可用的NNS解决IK问题,大多数现有的作品都采用定制的培训数据集,其中每个所需的姿势只有一个角度解决方案。这不可避免地限制了拟议方法的概括和自动化。本文在两个方面打破了:(1)一种涵盖机器人臂的整个工作空间的系统和机械方法,可以完全自动化,并且在手臂开发后只能完成一次; (2)一种基于NN的新型框架,可以利用冗余DOF为任何给定所需的机器人臂的姿势产生多角度解。后者对于机器人应用特别有用,例如避免障碍物和姿势模仿。
translated by 谷歌翻译
Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control. In this paper, we aim to answer the following question: does training the perception and control systems jointly end-toend provide better performance than training each component separately? To this end, we develop a method that can be used to learn policies that map raw image observations directly to torques at the robot's motors. The policies are represented by deep convolutional neural networks (CNNs) with 92,000 parameters, and are trained using a guided policy search method, which transforms policy search into supervised learning, with supervision provided by a simple trajectory-centric reinforcement learning method. We evaluate our method on a range of real-world manipulation tasks that require close coordination between vision and control, such as screwing a cap onto a bottle, and present simulated comparisons to a range of prior policy search methods.
translated by 谷歌翻译
We propose the tensorizing flow method for estimating high-dimensional probability density functions from the observed data. The method is based on tensor-train and flow-based generative modeling. Our method first efficiently constructs an approximate density in the tensor-train form via solving the tensor cores from a linear system based on the kernel density estimators of low-dimensional marginals. We then train a continuous-time flow model from this tensor-train density to the observed empirical distribution by performing a maximum likelihood estimation. The proposed method combines the optimization-less feature of the tensor-train with the flexibility of the flow-based generative models. Numerical results are included to demonstrate the performance of the proposed method.
translated by 谷歌翻译
在本文中,我们在不同研究领域使用的三种模型之间存在联系:来自正式语言和语言学的加权有限自动机〜(WFA),机器学习中使用的经常性神经网络,以及张量网络,包括一组高处的优化技术量子物理学和数值分析中使用的顺序张量。我们首先介绍WFA与张力列车分解,特定形式的张量网络之间的内在关系。该关系允许我们展示由WFA计算的函数的Hankel矩阵的新型低级结构,并设计利用这种结构的有效光谱学习算法来扩展到非常大的Hankel矩阵。我们将解开基本连接在WFA和第二阶逆转神经网络之间〜(2-RNN):在离散符号的序列的情况下,具有线性激活功能的WFA和2-RNN是表现性的。利用该等效结果与加权自动机的经典频谱学习算法相结合,我们介绍了在连续输入向量序列上定义的线性2-RNN的第一可提供学习算法。本算法依赖于Hankel Tensor的低等级子块,可以从中可以从中恢复线性2-RNN的参数。在综合性和现实世界数据的仿真研究中评估了所提出的学习算法的性能。
translated by 谷歌翻译
This survey provides an overview of higher-order tensor decompositions, their applications, and available software. A tensor is a multidimensional or N -way array. Decompositions of higher-order tensors (i.e., N -way arrays with N ≥ 3) have applications in psychometrics, chemometrics, signal processing, numerical linear algebra, computer vision, numerical analysis, data mining, neuroscience, graph analysis, and elsewhere. Two particular tensor decompositions can be considered to be higher-order extensions of the matrix singular value decomposition: CANDECOMP/PARAFAC (CP) decomposes a tensor as a sum of rank-one tensors, and the Tucker decomposition is a higher-order form of principal component analysis. There are many other tensor decompositions, including INDSCAL, PARAFAC2, CANDELINC, DEDICOM, and PARATUCK2 as well as nonnegative variants of all of the above. The N-way Toolbox, Tensor Toolbox, and Multilinear Engine are examples of software packages for working with tensors.
translated by 谷歌翻译
这本数字本书包含在物理模拟的背景下与深度学习相关的一切实际和全面的一切。尽可能多,所有主题都带有Jupyter笔记本的形式的动手代码示例,以便快速入门。除了标准的受监督学习的数据中,我们将看看物理丢失约束,更紧密耦合的学习算法,具有可微分的模拟,以及加强学习和不确定性建模。我们生活在令人兴奋的时期:这些方法具有从根本上改变计算机模拟可以实现的巨大潜力。
translated by 谷歌翻译
Sampling-based methods have become a cornerstone of contemporary approaches to Model Predictive Control (MPC), as they make no restrictions on the differentiability of the dynamics or cost function and are straightforward to parallelize. However, their efficacy is highly dependent on the quality of the sampling distribution itself, which is often assumed to be simple, like a Gaussian. This restriction can result in samples which are far from optimal, leading to poor performance. Recent work has explored improving the performance of MPC by sampling in a learned latent space of controls. However, these methods ultimately perform all MPC parameter updates and warm-starting between time steps in the control space. This requires us to rely on a number of heuristics for generating samples and updating the distribution and may lead to sub-optimal performance. Instead, we propose to carry out all operations in the latent space, allowing us to take full advantage of the learned distribution. Specifically, we frame the learning problem as bi-level optimization and show how to train the controller with backpropagation-through-time. By using a normalizing flow parameterization of the distribution, we can leverage its tractable density to avoid requiring differentiability of the dynamics and cost function. Finally, we evaluate the proposed approach on simulated robotics tasks and demonstrate its ability to surpass the performance of prior methods and scale better with a reduced number of samples.
translated by 谷歌翻译
Low-rank matrix approximations, such as the truncated singular value decomposition and the rank-revealing QR decomposition, play a central role in data analysis and scientific computing. This work surveys and extends recent research which demonstrates that randomization offers a powerful tool for performing low-rank matrix approximation. These techniques exploit modern computational architectures more fully than classical methods and open the possibility of dealing with truly massive data sets.This paper presents a modular framework for constructing randomized algorithms that compute partial matrix decompositions. These methods use random sampling to identify a subspace that captures most of the action of a matrix. The input matrix is then compressed-either explicitly or implicitly-to this subspace, and the reduced matrix is manipulated deterministically to obtain the desired low-rank factorization. In many cases, this approach beats its classical competitors in terms of accuracy, speed, and robustness. These claims are supported by extensive numerical experiments and a detailed error analysis.The specific benefits of randomized techniques depend on the computational environment. Consider the model problem of finding the k dominant components of the singular value decomposition of an m × n matrix. (i) For a dense input matrix, randomized algorithms require O(mn log(k)) floating-point operations (flops) in contrast with O(mnk) for classical algorithms. (ii) For a sparse input matrix, the flop count matches classical Krylov subspace methods, but the randomized approach is more robust and can easily be reorganized to exploit multi-processor architectures. (iii) For a matrix that is too large to fit in fast memory, the randomized techniques require only a constant number of passes over the data, as opposed to O(k) passes for classical algorithms. In fact, it is sometimes possible to perform matrix approximation with a single pass over the data.
translated by 谷歌翻译
Solving the analytical inverse kinematics (IK) of redundant manipulators in real time is a difficult problem in robotics since its solution for a given target pose is not unique. Moreover, choosing the optimal IK solution with respect to application-specific demands helps to improve the robustness and to increase the success rate when driving the manipulator from its current configuration towards a desired pose. This is necessary, especially in high-dynamic tasks like catching objects in mid-flights. To compute a suitable target configuration in the joint space for a given target pose in the trajectory planning context, various factors such as travel time or manipulability must be considered. However, these factors increase the complexity of the overall problem which impedes real-time implementation. In this paper, a real-time framework to compute the analytical inverse kinematics of a redundant robot is presented. To this end, the analytical IK of the redundant manipulator is parameterized by so-called redundancy parameters, which are combined with a target pose to yield a unique IK solution. Most existing works in the literature either try to approximate the direct mapping from the desired pose of the manipulator to the solution of the IK or cluster the entire workspace to find IK solutions. In contrast, the proposed framework directly learns these redundancy parameters by using a neural network (NN) that provides the optimal IK solution with respect to the manipulability and the closeness to the current robot configuration. Monte Carlo simulations show the effectiveness of the proposed approach which is accurate and real-time capable ($\approx$ \SI{32}{\micro\second}) on the KUKA LBR iiwa 14 R820.
translated by 谷歌翻译
本文提出了一个基于抽样的运动计划者,该计划将RRT*(迅速探索随机树星)集成到预计运动原始图的数据库中,以减轻其计算负载,并允许在动态或部分已知的环境中进行运动计划。该数据库是通过在某些网格空间中考虑一组初始状态和最终状态对来构建的,并确定每个对与系统动力学和约束兼容的最佳轨迹,同时最小化成本。通过在网格状态空间中提取样品并在数据库中选择将其连接到现有节点的数据库中的最佳无障碍运动原始性,将节点逐渐添加到RRT*算法中可行轨迹树中的节点。如果可以通过无障碍的运动原始的原始较低的成本从新的采样状态达到一些节点,则树将重新接线。因此,运动计划的计算更密集的部分被移至数据库构建的初步离线阶段(以网格造成的某些性能退化为代价。可以对网格分辨率进行调整,以便在数据库的最优性和大小之间妥协。由于网格分辨率为零,并且采样状态的数量增长到无穷大,因此规划器被证明是渐近的最佳选择。
translated by 谷歌翻译
Normalizing flows provide a general mechanism for defining expressive probability distributions, only requiring the specification of a (usually simple) base distribution and a series of bijective transformations. There has been much recent work on normalizing flows, ranging from improving their expressive power to expanding their application. We believe the field has now matured and is in need of a unified perspective. In this review, we attempt to provide such a perspective by describing flows through the lens of probabilistic modeling and inference. We place special emphasis on the fundamental principles of flow design, and discuss foundational topics such as expressive power and computational trade-offs. We also broaden the conceptual framing of flows by relating them to more general probability transformations. Lastly, we summarize the use of flows for tasks such as generative modeling, approximate inference, and supervised learning.
translated by 谷歌翻译