Human operators in human-robot teams are commonly perceived to be critical for mission success. To explore the direct and perceived impact of operator input on task success and team performance, 16 real-world missions (10 hrs) were conducted based on the DARPA Subterranean Challenge. These missions were to deploy a heterogeneous team of robots for a search task to locate and identify artifacts such as climbing rope, drills and mannequins representing human survivors. Two conditions were evaluated: human operators that could control the robot team with state-of-the-art autonomy (Human-Robot Team) compared to autonomous missions without human operator input (Robot-Autonomy). Human-Robot Teams were often in directed autonomy mode (70% of mission time), found more items, traversed more distance, covered more unique ground, and had a higher time between safety-related events. Human-Robot Teams were faster at finding the first artifact, but slower to respond to information from the robot team. In routine conditions, scores were comparable for artifacts, distance, and coverage. Reasons for intervention included creating waypoints to prioritise high-yield areas, and to navigate through error-prone spaces. After observing robot autonomy, operators reported increases in robot competency and trust, but that robot behaviour was not always transparent and understandable, even after high mission performance.

Our education system comprises a series of curricula. For example, when we learn mathematics at school, we learn in order from addition, to multiplication, and later to integration. Delineating a curriculum for teaching either a human or a machine shares the underlying goal of maximizing the positive knowledge transfer from early to later tasks and minimizing forgetting of the early tasks. Here, we exhaustively surveyed the effect of curricula on existing continual learning algorithms in the class-incremental setting, where algorithms must learn classes one at a time from a continuous stream of data. We observed that across a breadth of possible class orders (curricula), curricula influence the retention of information and that this effect is not just a product of stochasticity. Further, as a primary effort toward automated curriculum design, we proposed a method capable of designing and ranking effective curricula based on inter-class feature similarities. We compared the predicted curricula against empirically determined effectual curricula and observed significant overlaps between the two. To support the study of a curriculum designer, we conducted a series of human psychophysics experiments and contributed a new Continual Learning benchmark in object recognition. We assessed the degree of agreement in effective curricula between humans and machines. Surprisingly, our curriculum designer successfully predicts an optimal set of curricula that is effective for human learning. There are many considerations in curriculum design, such as timely student feedback and learning with multiple modalities. Our study is the first attempt to set a standard framework for the community to tackle the problem of teaching humans and machines to learn to learn continuously.

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.

生成对抗网络（GAN）是用于复杂数据生成建模的广泛使用的工具。尽管取得了经验成功，但由于发电机和鉴别器的最低最大优化，对GAN的训练尚未完全理解。本文分析了这些关节动力学时，当真实样品以及生成的样品是离散的，有限的集合，并且鉴别器基于内核。引入了一个简单而表达的框架，用于分析培训，称为$ \ textit {隔离点模型} $。在提出的模型中，真实样品之间的距离大大超过了内核宽度，因此每个生成的点都受到最多一个真实点的影响。我们的模型可以精确地表征好和不良最小值的收敛条件。特别是，分析解释了两种常见的故障模式：（i）近似模式崩溃和（ii）差异。提供了可预测复制这些行为的数值模拟。

我们提出了一个框架，该框架会自动将不可缩放的GNN转换为基于预典型的GNN，该GNN对于大型图表有效且可扩展。我们框架的优势是两倍。1）它通过将局部特征聚合与其图形卷积中的重量学习分开，2）通过将其边缘分解为小型图形，将其有效地在GPU上进行了预先执行，将各种局部特征聚合与重量学习分开，将各种局部特征聚合从重量学习中分离出来，从而使各种不可估计的GNN转换为大规模图表。和平衡的集合。通过大规模图的广泛实验，我们证明了转化的GNN在训练时间内的运行速度比现有的GNN更快，同时实现了最先进的GNN的竞争精度。因此，我们的转型框架为可伸缩GNN的未来研究提供了简单有效的基础。

The potential for complex systems to exhibit tipping points in which an equilibrium state undergoes a sudden and often irreversible shift is well established, but prediction of these events using standard forecast modeling techniques is quite difficult. This has led to the development of an alternative suite of methods that seek to identify signatures of critical phenomena in data, which are expected to occur in advance of many classes of dynamical bifurcation. Crucially, the manifestations of these critical phenomena are generic across a variety of systems, meaning that data-intensive deep learning methods can be trained on (abundant) synthetic data and plausibly prove effective when transferred to (more limited) empirical data sets. This paper provides a proof of concept for this approach as applied to lattice phase transitions: a deep neural network trained exclusively on 2D Ising model phase transitions is tested on a number of real and simulated climate systems with considerable success. Its accuracy frequently surpasses that of conventional statistical indicators, with performance shown to be consistently improved by the inclusion of spatial indicators. Tools such as this may offer valuable insight into climate tipping events, as remote sensing measurements provide increasingly abundant data on complex geospatially-resolved Earth systems.

有效的空间交通管理需要积极识别人造卫星。从观察到的数据中提取对象识别的当前方法需要空间分辨的图像，其限制对低地球轨道中的对象的标识。然而，大多数人造卫星在地球静止轨道上运行在距离的距离中，禁止基于地面的观察者解析空间信息。本文演示了一种物体识别解决方案，利用修改的残余卷积神经网络将远程不变光谱数据映射到对象标识。我们报告了模拟64级卫星问题超过80％的分类精度 - 即使在卫星正在进行恒定，随机重新定位的情况下。由这些结果驱动的天文观察活动，九级问题的精度为72％，平均每类的100个示例，按照模拟预期执行。我们展示了通过辍学，随机重量平均（SWA）和SWA集中的分层贝叶斯推断的应用，以测量空间交通管理中的分类不确定性 - 临界部件，其中日常决策昂贵的空间资产并承担地缘政治后果。

深度自身偏移通常具有监督或对抗的损失，以学习具有所需性质的潜在表示，例如对敏感变量的标签和结果或公平的更大预测性。尽管受到监督和对抗性深度潜在因子模型的难以致力于，但这些方法应该表现出更简单的线性方法在实践中优选的改进。这需要可重复的线性模拟，仍然遵守增强监督或对抗目标。我们通过提出使用监督或对冲目标的主成分分析（PCA）目标的方法来解决该方法论差距，并提供分析和可重复的解决方案。我们在开源Python软件包中实现这些方法，AugmentedPCA，可以生产出色的真实基础。我们证明了这些因子模型在开源的RNA-SEQ癌症基因表达数据集上的效用，表明增强具有监督目标，提高下游分类性能，产生具有更大级别保真度的主要成分，并有助于鉴定对齐的基因利用具有对特定类型癌症的发展的主要数据差异轴。

虽然深度加强学习（RL）代理商在获得机器人学的灵平行为方面表现出令人难以置信的潜力，但由于培训和执行环境之间的不匹配，它们倾向于在现实世界中部署时出现错误。相比之下，经典的机器人社区开发了一系列控制器，可以在真实的推导下，在现实世界中的大多数州都可以安全地操作。然而，这些控制器缺乏对分析建模和近似的局限性的复杂任务所需的灵活性。在本文中，我们提出了贝叶斯控制器融合（BCF），这是一种新颖的不确定性感知部署策略，这些策略结合了深度RL政策和传统手工控制器的优势。在本框架中，我们可以执行零拍摄的SIM-Teal Transfer，其中我们的不确定性的配方允许机器人通过利用手工制作的控制器来可靠地在分配状态下行动，同时获得所学习系统的灵敏度。我们在两个现实世界的连续控制任务上显示了有希望的结果，其中BCF优于独立的政策和控制器，超越了可以独立实现的。在HTTPS://bit.ly/bcf_deploy上提供演示我们系统的补充视频。

我们介绍了一个自主任务生成的对抗性网络（SATGAN），并将其应用于具有现实噪声模式和从收集数据中学习的现实噪声模式和传感器特性的常住空间对象的合成高对比度科学图像的问题。由于必须保留的数据中的语义内容的高度本地化，增强这些合成数据是具有挑战性的。真正收集的图像用于训练网络的特定传感器图像应该是什么样的网络。然后，培训的网络在嘈杂的上下文图像上用作过滤器，并输出具有未嵌入的语义内容的现实看起来。该架构由条件GANS启发，但被修改为包括通过增强保留语义信息的任务网络。另外，架构被示出为减少幻觉对象的情况或在表示空间观测场景的上下文图像中的语义内容的混淆。