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.

As the basis for prehensile manipulation, it is vital to enable robots to grasp as robustly as humans. In daily manipulation, our grasping system is prompt, accurate, flexible and continuous across spatial and temporal domains. Few existing methods cover all these properties for robot grasping. In this paper, we propose a new methodology for grasp perception to enable robots these abilities. Specifically, we develop a dense supervision strategy with real perception and analytic labels in the spatial-temporal domain. Additional awareness of objects' center-of-mass is incorporated into the learning process to help improve grasping stability. Utilization of grasp correspondence across observations enables dynamic grasp tracking. Our model, AnyGrasp, can generate accurate, full-DoF, dense and temporally-smooth grasp poses efficiently, and works robustly against large depth sensing noise. Embedded with AnyGrasp, we achieve a 93.3% success rate when clearing bins with over 300 unseen objects, which is comparable with human subjects under controlled conditions. Over 900 MPPH is reported on a single-arm system. For dynamic grasping, we demonstrate catching swimming robot fish in the water.

Video recognition in an open and dynamic world is quite challenging, as we need to handle different settings such as close-set, long-tail, few-shot and open-set. By leveraging semantic knowledge from noisy text descriptions crawled from the Internet, we focus on the general video recognition (GVR) problem of solving different recognition tasks within a unified framework. The core contribution of this paper is twofold. First, we build a comprehensive video recognition benchmark of Kinetics-GVR, including four sub-task datasets to cover the mentioned settings. To facilitate the research of GVR, we propose to utilize external textual knowledge from the Internet and provide multi-source text descriptions for all action classes. Second, inspired by the flexibility of language representation, we present a unified visual-linguistic framework (VLG) to solve the problem of GVR by an effective two-stage training paradigm. Our VLG is first pre-trained on video and language datasets to learn a shared feature space, and then devises a flexible bi-modal attention head to collaborate high-level semantic concepts under different settings. Extensive results show that our VLG obtains the state-of-the-art performance under four settings. The superior performance demonstrates the effectiveness and generalization ability of our proposed framework. We hope our work makes a step towards the general video recognition and could serve as a baseline for future research. The code and models will be available at https://github.com/MCG-NJU/VLG.

Recent success of vision transformers has inspired a series of vision backbones with novel feature transformation paradigms, which report steady performance gain. Although the novel feature transformation designs are often claimed as the source of gain, some backbones may benefit from advanced engineering techniques, which makes it hard to identify the real gain from the key feature transformation operators. In this paper, we aim to identify real gain of popular convolution and attention operators and make an in-depth study of them. We observe that the main difference among these feature transformation modules, e.g., attention or convolution, lies in the way of spatial feature aggregation, or the so-called "spatial token mixer" (STM). Hence, we first elaborate a unified architecture to eliminate the unfair impact of different engineering techniques, and then fit STMs into this architecture for comparison. Based on various experiments on upstream/downstream tasks and the analysis of inductive bias, we find that the engineering techniques boost the performance significantly, but the performance gap still exists among different STMs. The detailed analysis also reveals some interesting findings of different STMs, such as effective receptive fields and invariance tests. The code and trained models will be publicly available at https://github.com/OpenGVLab/STM-Evaluation

Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state. This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs. Different from the recent CNNs that focus on large dense kernels, InternImage takes deformable convolution as the core operator, so that our model not only has the large effective receptive field required for downstream tasks such as detection and segmentation, but also has the adaptive spatial aggregation conditioned by input and task information. As a result, the proposed InternImage reduces the strict inductive bias of traditional CNNs and makes it possible to learn stronger and more robust patterns with large-scale parameters from massive data like ViTs. The effectiveness of our model is proven on challenging benchmarks including ImageNet, COCO, and ADE20K. It is worth mentioning that InternImage-H achieved the new record 65.4 mAP on COCO test-dev. The code will be released at https://github.com/OpenGVLab/InternImage.

Starcraft II（SC2）对强化学习（RL）提出了巨大的挑战，其中主要困难包括巨大的状态空间，不同的动作空间和长期的视野。在这项工作中，我们研究了《星际争霸II》全长游戏的一系列RL技术。我们研究了涉及提取的宏观活动和神经网络的层次结构的层次RL方法。我们研究了课程转移培训程序，并在具有4个GPU和48个CPU线的单台计算机上训练代理。在64x64地图并使用限制性单元上，我们对内置AI的获胜率达到99％。通过课程转移学习算法和战斗模型的混合物，我们在最困难的非作战水平内置AI（7级）中获得了93％的胜利率。在本文的扩展版本中，我们改进了架构，以针对作弊水平训练代理商，并在8级，9级和10级AIS上达到胜利率，为96％，97％和94 ％， 分别。我们的代码在https://github.com/liuruoze/hiernet-sc2上。为了为我们的工作以及研究和开源社区提供基线，我们将其复制了一个缩放版本的Mini-Alphastar（MAS）。 MAS的最新版本为1.07，可以在具有564个动作的原始动作空间上进行培训。它旨在通过使超参数可调节来在单个普通机器上进行训练。然后，我们使用相同的资源将我们的工作与MAS进行比较，并表明我们的方法更有效。迷你α的代码在https://github.com/liuruoze/mini-alphastar上。我们希望我们的研究能够阐明对SC2和其他大型游戏有效增强学习的未来研究。

在鸟眼中学习强大的表现（BEV），以进行感知任务，这是趋势和吸引行业和学术界的广泛关注。大多数自动驾驶算法的常规方法在正面或透视视图中执行检测，细分，跟踪等。随着传感器配置变得越来越复杂，从不同的传感器中集成了多源信息，并在统一视图中代表功能至关重要。 BEV感知继承了几个优势，因为代表BEV中的周围场景是直观和融合友好的。对于BEV中的代表对象，对于随后的模块，如计划和/或控制是最可取的。 BEV感知的核心问题在于（a）如何通过从透视视图到BEV来通过视图转换来重建丢失的3D信息； （b）如何在BEV网格中获取地面真理注释； （c）如何制定管道以合并来自不同来源和视图的特征； （d）如何适应和概括算法作为传感器配置在不同情况下各不相同。在这项调查中，我们回顾了有关BEV感知的最新工作，并对不同解决方案进行了深入的分析。此外，还描述了该行业的BEV方法的几种系统设计。此外，我们推出了一套完整的实用指南，以提高BEV感知任务的性能，包括相机，激光雷达和融合输入。最后，我们指出了该领域的未来研究指示。我们希望该报告能阐明社区，并鼓励对BEV感知的更多研究。我们保留一个活跃的存储库来收集最新的工作，并在https://github.com/openperceptionx/bevperception-survey-recipe上提供一包技巧的工具箱。

逐渐射击的语义分割（IFSS）目标以逐步扩展模型的能力逐渐扩大了仅由几个样本监督的新图像。但是，在旧课程中学到的特征可能会大大漂移，从而导致灾难性遗忘。此外，很少有针对新课程的像素级细分样本会导致每个学习课程中臭名昭著的过度拟合问题。在本文中，我们明确表示基于类别的语义分割的知识作为类别嵌入和超级类嵌入，前者描述了独家的语义属性，而后者则表示超级类知识作为类共享语义属性。为了解决IFSS问题，我们提出了EHNET，即从两个方面嵌入自适应更高和超级级表示网络。首先，我们提出了一种嵌入自适应的策略，以避免特征漂移，该策略通过超级班级表示保持旧知识，并使用类似课程的方案自适应地更新类别嵌入类别，以涉及在各个会话中学习的新课程。其次，为了抵制很少有培训样本引起的过度拟合问题，通过将所有类别嵌入以进行初始化并与新班级的类别保持一致以进行增强，从而学习了超级班级的嵌入，从而使学会知识有助于学习新知识，从而减轻了绩效绩效的绩效，依赖培训数据量表。值得注意的是，这两种设计为具有足够语义和有限偏见的类提供了表示能力，从而可以执行需要高语义依赖性的分割任务。 Pascal-5i和可可数据集的实验表明，EHNET具有显着优势的新最先进的性能。

为了构建人工神经网络，例如生物智能系统，最近的作品将许多任务统一为通才模型，该模型可以使用共享参数处理各种任务，并且没有任何特定于任务的模块。尽管通才模型在各种基准上取得了令人鼓舞的结果，但与任务特殊模型相比，它们在某些任务上具有绩效降解。在这项工作中，我们发现不同任务和方式之间的干扰是这种现象的主要因素。为了减轻这种干扰，我们将条件混合物（条件MOE）引入通才模型。建议在不同级别的条件下采用路由策略来考虑培训/推理成本和概括能力。通过合并提出的条件MOE，最近提出的通才模型Uni-Pectiver可以有效地减轻任务和方式的干扰，并通过迅速调整1％的下游数据，从而在一系列下游任务上实现最新的结果。 。此外，有条件的MOE的引入仍然具有通才模型对新任务（例如视频文本检索和视频标题）进行零摄像推断的概括能力。应发布代码和预培训的通才模型。

3D视觉感知任务，包括基于多相机图像的3D检测和MAP分割，对于自主驾驶系统至关重要。在这项工作中，我们提出了一个称为BeVformer的新框架，该框架以时空变压器学习统一的BEV表示，以支持多个自主驾驶感知任务。简而言之，Bevormer通过通过预定义的网格形BEV查询与空间和时间空间进行交互来利用空间和时间信息。为了汇总空间信息，我们设计了空间交叉注意，每个BEV查询都从相机视图中从感兴趣的区域提取了空间特征。对于时间信息，我们提出暂时的自我注意力，以将历史bev信息偶尔融合。我们的方法在Nuscenes \ texttt {test} set上，以NDS度量为单位达到了新的最新56.9 \％，该设置比以前的最佳艺术高9.0分，并且与基于LIDAR的盆地的性能相当。我们进一步表明，BeVormer明显提高了速度估计的准确性和在低可见性条件下对象的回忆。该代码可在\ url {https://github.com/zhiqi-li/bevformer}中获得。