如果我们想在将它们部署在现实中之前在模拟中训练机器人，那么假定减少SIM2REAL差距的人似乎很自然，并且几乎是不言而喻的，涉及创建富裕性的模拟器（因为现实就是事实）。我们挑战了这一假设并提出了相反的假设-SIM2REAL转移机器人可以通过较低（不是更高）的保真度模拟来改善。我们使用3种不同的机器人（A1，Aliengo，Spot）对这一假设进行了系统的大规模评估 - 在现实世界中以及2个不同的模拟器（栖息地和Igibson）。我们的结果表明，与期望相反，增加忠诚无助于学习。由于模拟速度缓慢（防止大规模学习）和对模拟物理学不准确的过度拟合，因此性能较差。取而代之的是，使用现实世界数据构建机器人运动的简单模型可以改善学习和概括。

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。 。

Classification bandits are multi-armed bandit problems whose task is to classify a given set of arms into either positive or negative class depending on whether the rate of the arms with the expected reward of at least h is not less than w for given thresholds h and w. We study a special classification bandit problem in which arms correspond to points x in d-dimensional real space with expected rewards f(x) which are generated according to a Gaussian process prior. We develop a framework algorithm for the problem using various arm selection policies and propose policies called FCB and FTSV. We show a smaller sample complexity upper bound for FCB than that for the existing algorithm of the level set estimation, in which whether f(x) is at least h or not must be decided for every arm's x. Arm selection policies depending on an estimated rate of arms with rewards of at least h are also proposed and shown to improve empirical sample complexity. According to our experimental results, the rate-estimation versions of FCB and FTSV, together with that of the popular active learning policy that selects the point with the maximum variance, outperform other policies for synthetic functions, and the version of FTSV is also the best performer for our real-world dataset.

Esports, a sports competition using video games, has become one of the most important sporting events in recent years. Although the amount of esports data is increasing than ever, only a small fraction of those data accompanies text commentaries for the audience to retrieve and understand the plays. Therefore, in this study, we introduce a task of generating game commentaries from structured data records to address the problem. We first build a large-scale esports data-to-text dataset using structured data and commentaries from a popular esports game, League of Legends. On this dataset, we devise several data preprocessing methods including linearization and data splitting to augment its quality. We then introduce several baseline encoder-decoder models and propose a hierarchical model to generate game commentaries. Considering the characteristics of esports commentaries, we design evaluation metrics including three aspects of the output: correctness, fluency, and strategic depth. Experimental results on our large-scale esports dataset confirmed the advantage of the hierarchical model, and the results revealed several challenges of this novel task.

Learning-from-Observation (LfO) is a robot teaching framework for programming operations through few-shots human demonstration. While most previous LfO systems run with visual demonstration, recent research on robot teaching has shown the effectiveness of verbal instruction in making recognition robust and teaching interactive. To the best of our knowledge, however, few solutions have been proposed for LfO that utilizes verbal instruction, namely multimodal LfO. This paper aims to propose a practical pipeline for multimodal LfO. For input, an user temporally stops hand movements to match the granularity of human instructions with the granularity of robot execution. The pipeline recognizes tasks based on step-by-step verbal instructions accompanied by demonstrations. In addition, the recognition is made robust through interactions with the user. We test the pipeline on a real robot and show that the user can successfully teach multiple operations from multimodal demonstrations. The results suggest the utility of the proposed pipeline for multimodal LfO.

Robot developers develop various types of robots for satisfying users' various demands. Users' demands are related to their backgrounds and robots suitable for users may vary. If a certain developer would offer a robot that is different from the usual to a user, the robot-specific software has to be changed. On the other hand, robot-software developers would like to reuse their developed software as much as possible to reduce their efforts. We propose the system design considering hardware-level reusability. For this purpose, we begin with the learning-from-observation framework. This framework represents a target task in robot-agnostic representation, and thus the represented task description can be shared with various robots. When executing the task, it is necessary to convert the robot-agnostic description into commands of a target robot. To increase the reusability, first, we implement the skill library, robot motion primitives, only considering a robot hand and we regarded that a robot was just a carrier to move the hand on the target trajectory. The skill library is reusable if we would like to the same robot hand. Second, we employ the generic IK solver to quickly swap a robot. We verify the hardware-level reusability by applying two task descriptions to two different robots, Nextage and Fetch.

Deep learning (DL) has become a driving force and has been widely adopted in many domains and applications with competitive performance. In practice, to solve the nontrivial and complicated tasks in real-world applications, DL is often not used standalone, but instead contributes as a piece of gadget of a larger complex AI system. Although there comes a fast increasing trend to study the quality issues of deep neural networks (DNNs) at the model level, few studies have been performed to investigate the quality of DNNs at both the unit level and the potential impacts on the system level. More importantly, it also lacks systematic investigation on how to perform the risk assessment for AI systems from unit level to system level. To bridge this gap, this paper initiates an early exploratory study of AI system risk assessment from both the data distribution and uncertainty angles to address these issues. We propose a general framework with an exploratory study for analyzing AI systems. After large-scale (700+ experimental configurations and 5000+ GPU hours) experiments and in-depth investigations, we reached a few key interesting findings that highlight the practical need and opportunities for more in-depth investigations into AI systems.

Human pose estimation, particularly in athletes, can help improve their performance. However, this estimation is difficult using existing methods, such as human annotation, if the subjects wear loose-fitting clothes such as ski/snowboard wears. This study developed a method for obtaining the ground truth data on two-dimensional (2D) poses of a human wearing loose-fitting clothes. This method uses fast-flushing light-emitting diodes (LEDs). The subjects were required to wear loose-fitting clothes and place the LED on the target joints. The LEDs were observed directly using a camera by selecting thin filmy loose-fitting clothes. The proposed method captures the scene at 240 fps by using a high-frame-rate camera and renders two 30 fps image sequences by extracting LED-on and -off frames. The temporal differences between the two video sequences can be ignored, considering the speed of human motion. The LED-on video was used to manually annotate the joints and thus obtain the ground truth data. Additionally, the LED-off video, equivalent to a standard video at 30 fps, confirmed the accuracy of existing machine learning-based methods and manual annotations. Experiments demonstrated that the proposed method can obtain ground truth data for standard RGB videos. Further, it was revealed that neither manual annotation nor the state-of-the-art pose estimator obtains the correct position of target joints.

Generative models, particularly GANs, have been utilized for image editing. Although GAN-based methods perform well on generating reasonable contents aligned with the user's intentions, they struggle to strictly preserve the contents outside the editing region. To address this issue, we use diffusion models instead of GANs and propose a novel image-editing method, based on pixel-wise guidance. Specifically, we first train pixel-classifiers with few annotated data and then estimate the semantic segmentation map of a target image. Users then manipulate the map to instruct how the image is to be edited. The diffusion model generates an edited image via guidance by pixel-wise classifiers, such that the resultant image aligns with the manipulated map. As the guidance is conducted pixel-wise, the proposed method can create reasonable contents in the editing region while preserving the contents outside this region. The experimental results validate the advantages of the proposed method both quantitatively and qualitatively.

Removing reverb from reverberant music is a necessary technique to clean up audio for downstream music manipulations. Reverberation of music contains two categories, natural reverb, and artificial reverb. Artificial reverb has a wider diversity than natural reverb due to its various parameter setups and reverberation types. However, recent supervised dereverberation methods may fail because they rely on sufficiently diverse and numerous pairs of reverberant observations and retrieved data for training in order to be generalizable to unseen observations during inference. To resolve these problems, we propose an unsupervised method that can remove a general kind of artificial reverb for music without requiring pairs of data for training. The proposed method is based on diffusion models, where it initializes the unknown reverberation operator with a conventional signal processing technique and simultaneously refines the estimate with the help of diffusion models. We show through objective and perceptual evaluations that our method outperforms the current leading vocal dereverberation benchmarks.