电缆在许多环境中无处不在,但容易出现自我闭合和结,使它们难以感知和操纵。挑战通常会随着电缆长度而增加:长电缆需要更复杂的松弛管理和策略,以促进可观察性和可及性。在本文中,我们专注于使用双边机器人自动弄清长达3米的电缆。我们开发了新的运动原语,以有效地解开长电缆和专门用于此任务的新型Gripper Jaws。我们提出了缠结操作(SGTM)的滑动和抓握,该算法将这些原始物与RGBD视觉构成迭代性毫无障碍。SGTM在隔离的外手上取消了67%的成功率,图8节和更复杂的配置上的50%。可以在https://sites.google.com/view/rss-2022-untangling/home上找到补充材料,可视化和视频。
translated by 谷歌翻译
最近的工作表明,2臂“ Fling”运动对于服装平滑可能是有效的。我们考虑单臂弹性运动。与几乎不需要机器人轨迹参数调整的2臂fling运动不同,单臂fling运动对轨迹参数很敏感。我们考虑一个单一的6多机器人臂,该机器人臂学习跨越轨迹以实现高衣覆盖率。给定服装抓握点,机器人在物理实验中探索了不同的参数化fling轨迹。为了提高学习效率,我们提出了一种粗到精细的学习方法,该方法首先使用多军匪徒(MAB)框架有效地找到候选动作,然后通过连续优化方法来完善。此外,我们提出了基于Fling Fall结果不确定性的新颖培训和执行时间停止标准。与基线相比,我们表明所提出的方法显着加速学习。此外,由于通过自学人员收集的类似服装的先前经验,新服装的MAB学习时间最多减少了87%。我们评估了6种服装类型:毛巾,T恤,长袖衬衫,礼服,汗衫和牛仔裤。结果表明,使用先前的经验,机器人需要30分钟以下的时间才能为达到60-94%覆盖率的新型服装学习一项动作。
translated by 谷歌翻译
使用单个参数化动态动作操纵可变形物体对蝇钓,宽毯和播放洗牌板等任务非常有用。此类任务作为输入所需的最终状态并输出一个参数化的开环动态机器人动作,它向最终状态产生轨迹。这对于具有涉及摩擦力的复杂动态的长地平轨迹尤其具有挑战性。本文探讨了平面机器人铸造的任务(PRC):其中握住电缆一端的机器人手腕的一个平面运动使另一端朝向所需的目标滑过平面。 PRC允许电缆达到机器人工作区以外的点,并在家庭,仓库和工厂中具有电缆管理的应用。为了有效地学习给定电缆的PRC策略,我们提出了Real2Sim2Real,一个自动收集物理轨迹示例的自我监督框架,以使用差分演进调谐动态模拟器的参数,生成许多模拟示例,然后使用加权学习策略模拟和物理数据的组合。我们使用三种模拟器,ISAAC健身房分段,ISAAC健身房 - 混合动力和Pybullet,两个功能近似器,高斯工艺和神经网络(NNS),以及具有不同刚度,扭转和摩擦的三个电缆。结果每条电缆的16个举出的测试目标表明,使用ISAAC健身房分段的NN PRC策略达到中位误差距离(电缆长度的百分比),范围为8%至14%,表现优于真实或仅培训的基线和政策。只有模拟的例子。 https://tinyurl.com/robotcast可以使用代码,数据和视频。
translated by 谷歌翻译
The body of research on classification of solar panel arrays from aerial imagery is increasing, yet there are still not many public benchmark datasets. This paper introduces two novel benchmark datasets for classifying and localizing solar panel arrays in Denmark: A human annotated dataset for classification and segmentation, as well as a classification dataset acquired using self-reported data from the Danish national building registry. We explore the performance of prior works on the new benchmark dataset, and present results after fine-tuning models using a similar approach as recent works. Furthermore, we train models of newer architectures and provide benchmark baselines to our datasets in several scenarios. We believe the release of these datasets may improve future research in both local and global geospatial domains for identifying and mapping of solar panel arrays from aerial imagery. The data is accessible at https://osf.io/aj539/.
translated by 谷歌翻译
This is a continuation of our recent paper in which we developed the theory of sequential parametrized motion planning. A sequential parametrized motion planning algorithm produced a motion of the system which is required to visit a prescribed sequence of states, in a certain order, at specified moments of time. In the previous publication we analysed the sequential parametrized topological complexity of the Fadell - Neuwirth fibration which in relevant to the problem of moving multiple robots avoiding collisions with other robots and with obstacles in the Euclidean space. Besides, in the preceeding paper we found the sequential parametrised topological complexity of the Fadell - Neuwirth bundle for the case of the Euclidean space $\Bbb R^d$ of odd dimension as well as the case $d=2$. In the present paper we give the complete answer for an arbitrary $d\ge 2$ even. Moreover, we present an explicit motion planning algorithm for controlling multiple robots in $\Bbb R^d$ having the minimal possible topological complexity; this algorithm is applicable to any number $n$ of robots and any number $m\ge 2$ of obstacles.
translated by 谷歌翻译
The proliferation of unmanned aircraft systems (UAS) has caused airspace regulation authorities to examine the interoperability of these aircraft with collision avoidance systems initially designed for large transport category aircraft. Limitations in the currently mandated TCAS led the Federal Aviation Administration to commission the development of a new solution, the Airborne Collision Avoidance System X (ACAS X), designed to enable a collision avoidance capability for multiple aircraft platforms, including UAS. While prior research explored using deep reinforcement learning algorithms (DRL) for collision avoidance, DRL did not perform as well as existing solutions. This work explores the benefits of using a DRL collision avoidance system whose parameters are tuned using a surrogate optimizer. We show the use of a surrogate optimizer leads to DRL approach that can increase safety and operational viability and support future capability development for UAS collision avoidance.
translated by 谷歌翻译
This paper describes important considerations and challenges associated with online reinforcement-learning based waveform selection for target identification in frequency modulated continuous wave (FMCW) automotive radar systems. We present a novel learning approach based on satisficing Thompson sampling, which quickly identifies a waveform expected to yield satisfactory classification performance. We demonstrate through measurement-level simulations that effective waveform selection strategies can be quickly learned, even in cases where the radar must select from a large catalog of candidate waveforms. The radar learns to adaptively select a bandwidth for appropriate resolution and a slow-time unimodular code for interference mitigation in the scene of interest by optimizing an expected classification metric.
translated by 谷歌翻译
The capture and animation of human hair are two of the major challenges in the creation of realistic avatars for the virtual reality. Both problems are highly challenging, because hair has complex geometry and appearance, as well as exhibits challenging motion. In this paper, we present a two-stage approach that models hair independently from the head to address these challenges in a data-driven manner. The first stage, state compression, learns a low-dimensional latent space of 3D hair states containing motion and appearance, via a novel autoencoder-as-a-tracker strategy. To better disentangle the hair and head in appearance learning, we employ multi-view hair segmentation masks in combination with a differentiable volumetric renderer. The second stage learns a novel hair dynamics model that performs temporal hair transfer based on the discovered latent codes. To enforce higher stability while driving our dynamics model, we employ the 3D point-cloud autoencoder from the compression stage for de-noising of the hair state. Our model outperforms the state of the art in novel view synthesis and is capable of creating novel hair animations without having to rely on hair observations as a driving signal.
translated by 谷歌翻译
When should an online reinforcement learning-based frequency agile cognitive radar be expected to outperform a rule-based adaptive waveform selection strategy? We seek insight regarding this question by examining a dynamic spectrum access scenario, in which the radar wishes to transmit in the widest unoccupied bandwidth during each pulse repetition interval. Online learning is compared to a fixed rule-based sense-and-avoid strategy. We show that given a simple Markov channel model, the problem can be examined analytically for simple cases via stochastic dominance. Additionally, we show that for more realistic channel assumptions, learning-based approaches demonstrate greater ability to generalize. However, for short time-horizon problems that are well-specified, we find that machine learning approaches may perform poorly due to the inherent limitation of convergence time. We draw conclusions as to when learning-based approaches are expected to be beneficial and provide guidelines for future study.
translated by 谷歌翻译
Since higher-order tensors are naturally suitable for representing multi-dimensional data in real-world, e.g., color images and videos, low-rank tensor representation has become one of the emerging areas in machine learning and computer vision. However, classical low-rank tensor representations can only represent data on finite meshgrid due to their intrinsical discrete nature, which hinders their potential applicability in many scenarios beyond meshgrid. To break this barrier, we propose a low-rank tensor function representation (LRTFR), which can continuously represent data beyond meshgrid with infinite resolution. Specifically, the suggested tensor function, which maps an arbitrary coordinate to the corresponding value, can continuously represent data in an infinite real space. Parallel to discrete tensors, we develop two fundamental concepts for tensor functions, i.e., the tensor function rank and low-rank tensor function factorization. We theoretically justify that both low-rank and smooth regularizations are harmoniously unified in the LRTFR, which leads to high effectiveness and efficiency for data continuous representation. Extensive multi-dimensional data recovery applications arising from image processing (image inpainting and denoising), machine learning (hyperparameter optimization), and computer graphics (point cloud upsampling) substantiate the superiority and versatility of our method as compared with state-of-the-art methods. Especially, the experiments beyond the original meshgrid resolution (hyperparameter optimization) or even beyond meshgrid (point cloud upsampling) validate the favorable performances of our method for continuous representation.
translated by 谷歌翻译