Learning efficient and interpretable policies has been a challenging task in reinforcement learning (RL), particularly in the visual RL setting with complex scenes. While neural networks have achieved competitive performance, the resulting policies are often over-parameterized black boxes that are difficult to interpret and deploy efficiently. More recent symbolic RL frameworks have shown that high-level domain-specific programming logic can be designed to handle both policy learning and symbolic planning. However, these approaches rely on coded primitives with little feature learning, and when applied to high-dimensional visual scenes, they can suffer from scalability issues and perform poorly when images have complex object interactions. To address these challenges, we propose \textit{Differentiable Symbolic Expression Search} (DiffSES), a novel symbolic learning approach that discovers discrete symbolic policies using partially differentiable optimization. By using object-level abstractions instead of raw pixel-level inputs, DiffSES is able to leverage the simplicity and scalability advantages of symbolic expressions, while also incorporating the strengths of neural networks for feature learning and optimization. Our experiments demonstrate that DiffSES is able to generate symbolic policies that are simpler and more and scalable than state-of-the-art symbolic RL methods, with a reduced amount of symbolic prior knowledge.

Denoising Diffusion Probabilistic Models (DDPMs) are emerging in text-to-speech (TTS) synthesis because of their strong capability of generating high-fidelity samples. However, their iterative refinement process in high-dimensional data space results in slow inference speed, which restricts their application in real-time systems. Previous works have explored speeding up by minimizing the number of inference steps but at the cost of sample quality. In this work, to improve the inference speed for DDPM-based TTS model while achieving high sample quality, we propose ResGrad, a lightweight diffusion model which learns to refine the output spectrogram of an existing TTS model (e.g., FastSpeech 2) by predicting the residual between the model output and the corresponding ground-truth speech. ResGrad has several advantages: 1) Compare with other acceleration methods for DDPM which need to synthesize speech from scratch, ResGrad reduces the complexity of task by changing the generation target from ground-truth mel-spectrogram to the residual, resulting into a more lightweight model and thus a smaller real-time factor. 2) ResGrad is employed in the inference process of the existing TTS model in a plug-and-play way, without re-training this model. We verify ResGrad on the single-speaker dataset LJSpeech and two more challenging datasets with multiple speakers (LibriTTS) and high sampling rate (VCTK). Experimental results show that in comparison with other speed-up methods of DDPMs: 1) ResGrad achieves better sample quality with the same inference speed measured by real-time factor; 2) with similar speech quality, ResGrad synthesizes speech faster than baseline methods by more than 10 times. Audio samples are available at https://resgrad1.github.io/.

Modern autonomous driving system is characterized as modular tasks in sequential order, i.e., perception, prediction and planning. As sensors and hardware get improved, there is trending popularity to devise a system that can perform a wide diversity of tasks to fulfill higher-level intelligence. Contemporary approaches resort to either deploying standalone models for individual tasks, or designing a multi-task paradigm with separate heads. These might suffer from accumulative error or negative transfer effect. Instead, we argue that a favorable algorithm framework should be devised and optimized in pursuit of the ultimate goal, i.e. planning of the self-driving-car. Oriented at this goal, we revisit the key components within perception and prediction. We analyze each module and prioritize the tasks hierarchically, such that all these tasks contribute to planning (the goal). To this end, we introduce Unified Autonomous Driving (UniAD), the first comprehensive framework up-to-date that incorporates full-stack driving tasks in one network. It is exquisitely devised to leverage advantages of each module, and provide complementary feature abstractions for agent interaction from a global perspective. Tasks are communicated with unified query design to facilitate each other toward planning. We instantiate UniAD on the challenging nuScenes benchmark. With extensive ablations, the effectiveness of using such a philosophy is proven to surpass previous state-of-the-arts by a large margin in all aspects. The full suite of codebase and models would be available to facilitate future research in the community.

像有声读物的综合一样，表达性语音综合仍然对样式表示学习和预测仍然具有挑战性。从参考音频或从文本预测样式标签中得出的标签需要大量标记的数据，这是昂贵的，并且难以准确定义和注释。在本文中，我们提出了一个新颖的框架，以一种自我监督的方式从丰富的纯文本中学习样式表示。它利用情感词典，并使用对比度学习和深度聚类。我们进一步将样式表示形式整合为多式变压器TTS中的条件嵌入。通过预测在同一数据集上训练的样式标签，但通过人类注释，我们的方法根据对声音域内和室外测试集的主观评估来改进结果，从而获得了改进的结果。此外，有了隐性的背景感知样式表示，长期综合音频的情感过渡似乎更自然。音频样本可在演示网络上找到。

如最近的研究所示，支持机器智能的系统容易受到对抗性操纵或自然分配变化产生的测试案例的影响。这引起了人们对现实应用程序部署机器学习算法的极大关注，尤其是在自动驾驶（AD）等安全性领域中。另一方面，由于自然主义场景的传统广告测试需要数亿英里，这是由于现实世界中安全关键方案的高度和稀有性。结果，已经探索了几种自动驾驶评估方法，但是，这些方法通常是基于不同的仿真平台，安全性 - 关键的情况的类型，场景生成算法和驾驶路线变化的方法。因此，尽管在自动驾驶测试方面进行了大量努力，但在相似条件下，比较和了解不同测试场景产生算法和测试机制的有效性和效率仍然是一项挑战。在本文中，我们旨在提供第一个统一的平台Safebench，以整合不同类型的安全性测试方案，场景生成算法以及其他变体，例如驾驶路线和环境。同时，我们实施了4种基于深入学习的AD算法，具有4种类型的输入（例如，鸟类视图，相机，相机），以对SafeBench进行公平的比较。我们发现，我们的生成的测试场景确实更具挑战性，并观察到在良性和关键安全测试方案下的广告代理的性能之间的权衡。我们认为，我们的统一平台安全基地用于大规模和有效的自动驾驶测试，将激发新的测试场景生成和安全AD算法的开发。 SafeBench可从https://safebench.github.io获得。

姿势估计在以人为本的视力应用中起关键作用。但是，由于高计算成本（每帧超过150 GMAC），很难在资源受限的边缘设备上部署最新的基于HRNET的姿势估计模型。在本文中，我们研究了在边缘实时多人姿势估计的有效体系结构设计。我们透露，通过我们的逐渐收缩实验，HRNET的高分辨率分支对于低计量区域的模型是多余的。删除它们可以提高效率和性能。受这一发现的启发，我们设计了LitePose，这是一种有效的单分支架构，用于姿势估计，并引入了两种简单的方法来增强LitePose的能力，包括Fusion Deconv Head和大型内核Corvs。 Fusion deconv头部删除了高分辨率分支中的冗余，从而使尺度感知的特征融合且开销低。大型内核会大大提高模型的能力和接受场，同时保持低计算成本。只有25％的计算增量，7x7内核的实现+14.0地图优于人群数据集上的3x3内核。在移动平台上，LitePose与先前最新的有效姿势估计模型相比，LitePose将潜伏期最高可达5.0倍，而无需牺牲性能，从而推动了实时多人姿势估计的边界。我们的代码和预培训模型在https://github.com/mit-han-lab/litepose上发布。

Accurate and smooth global navigation satellite system (GNSS) positioning for pedestrians in urban canyons is still a challenge due to the multipath effects and the non-light-of-sight (NLOS) receptions caused by the reflections from surrounding buildings. The recently developed factor graph optimization (FGO) based GNSS positioning method opened a new window for improving urban GNSS positioning by effectively exploiting the measurement redundancy from the historical information to resist the outlier measurements. Unfortunately, the FGO-based GNSS standalone positioning is still challenged in highly urbanized areas. As an extension of the previous FGO-based GNSS positioning method, this paper exploits the potential of the pedestrian dead reckoning (PDR) model in FGO to improve the GNSS standalone positioning performance in urban canyons. Specifically, the relative motion of the pedestrian is estimated based on the raw acceleration measurements from the onboard smartphone inertial measurement unit (IMU) via the PDR algorithm. Then the raw GNSS pseudorange, Doppler measurements, and relative motion from PDR are integrated using the FGO. Given the context of pedestrian navigation with a small acceleration most of the time, a novel soft motion model is proposed to smooth the states involved in the factor graph model. The effectiveness of the proposed method is verified step-by-step through two datasets collected in dense urban canyons of Hong Kong using smartphone-level GNSS receivers. The comparison between the conventional extended Kalman filter, several existing methods, and FGO-based integration is presented. The results reveal that the existing FGO-based GNSS standalone positioning is highly complementary to the PDR's relative motion estimation. Both improved positioning accuracy and trajectory smoothness are obtained with the help of the proposed method.

A lot of theoretical and empirical evidence shows that the flatter local minima tend to improve generalization. Adversarial Weight Perturbation (AWP) is an emerging technique to efficiently and effectively find such minima. In AWP we minimize the loss w.r.t. a bounded worst-case perturbation of the model parameters thereby favoring local minima with a small loss in a neighborhood around them. The benefits of AWP, and more generally the connections between flatness and generalization, have been extensively studied for i.i.d. data such as images. In this paper, we extensively study this phenomenon for graph data. Along the way, we first derive a generalization bound for non-i.i.d. node classification tasks. Then we identify a vanishing-gradient issue with all existing formulations of AWP and we propose a new Weighted Truncated AWP (WT-AWP) to alleviate this issue. We show that regularizing graph neural networks with WT-AWP consistently improves both natural and robust generalization across many different graph learning tasks and models.

This paper presents the TransBoat, a novel omnidirectional unmanned surface vehicle (USV) with a magnetbased docking system for overwater construction with wave disturbances. This is the first such USV that can build overwater structures by transporting modules. The TransBoat incorporates two features designed to reject wave disturbances. First, the TransBoat's expandable body structure can actively transform from a mono-hull into a multi-hull for stabilization in turbulent environments by extending its four outrigger hulls. Second, a real-time nonlinear model predictive control (NMPC) scheme is proposed for all shapes of the TransBoat to enhance its maneuverability and resist disturbance to its movement, based on a nonlinear dynamic model. An experimental approach is proposed to identify the parameters of the dynamic model, and a subsequent trajectory tracking test validates the dynamics, NMPC controller and system mobility. Further, docking experiments identify improved performance in the expanded form of the TransBoat compared with the contracted form, including an increased success rate (of ~ 10%) and reduced docking time (of ~ 40 s on average). Finally, a bridge construction test verifies our system design and the NMPC control method.

Video dubbing aims to translate the original speech in a film or television program into the speech in a target language, which can be achieved with a cascaded system consisting of speech recognition, machine translation and speech synthesis. To ensure the translated speech to be well aligned with the corresponding video, the length/duration of the translated speech should be as close as possible to that of the original speech, which requires strict length control. Previous works usually control the number of words or characters generated by the machine translation model to be similar to the source sentence, without considering the isochronicity of speech as the speech duration of words/characters in different languages varies. In this paper, we propose a machine translation system tailored for the task of video dubbing, which directly considers the speech duration of each token in translation, to match the length of source and target speech. Specifically, we control the speech length of generated sentence by guiding the prediction of each word with the duration information, including the speech duration of itself as well as how much duration is left for the remaining words. We design experiments on four language directions (German -> English, Spanish -> English, Chinese <-> English), and the results show that the proposed method achieves better length control ability on the generated speech than baseline methods. To make up the lack of real-world datasets, we also construct a real-world test set collected from films to provide comprehensive evaluations on the video dubbing task.