长期以来，Robotics一直是一个遍布复杂系统体系结构的领域，无论传统或基于学习的模块和联系都需要大量的人类专业知识和先验知识。受大型预训练语言模型的启发，这项工作引入了预先培训的通用表示范式，该范式可以作为给定机器人多个任务的起点。我们提出了感知性因果变压器（PACT），这是一种基于生成变压器的架构，旨在以自我监督的方式直接从机器人数据构建表示形式。通过对状态和行动的自动回归预测，我们的模型隐含地编码了特定机器人的动态和行为。我们的实验评估重点是移动药物的域，我们表明该机器人特定的表示可以作为单个起点，以实现不同的任务，例如安全导航，定位和映射。我们评估了两个形式：使用激光雷达传感器作为感知输入（MUSHR）的轮式机器人，以及使用第一人称RGB图像（栖息地）的模拟药物。我们表明，与训练单个模型的同时训练单个模型相比，对所有任务的单个模型进行训练，并且与独立培训单独的大型模型相当的性能，对每个任务的单个模型进行了可比的训练，则在较大的审计模型上进行了固定小型任务特异性网络，从而使性能明显提高。通过跨任务共享共同的优质表示，我们可以降低整体模型容量并加快此类系统的实时部署。

自然语言是表达人类意图的最直观的方式之一。但是，将指示和命令转换为机器人运动生产以及在现实世界中的部署，远非一件容易的事。的确，将机器人的固有的低水平几何形状和运动动力学约束与人类的高级语义信息相结合，振奋人心，并提出了对任务设计问题的新挑战 - 通常会通过一组静态的动作目标和命令来实现任务或硬件特定的解决方案。相反，这项工作提出了一个灵活的基于语言的框架，该框架允许使用有关先前任务或机器人信息的限制的语言命令修改通用3D机器人轨迹。通过利用预训练的语言模型，我们使用自动回归变压器将自然语言输入和上下文图像映射到3D轨迹中的变化中。我们通过模拟和现实生活实验表明，该模型可以成功遵循人类的意图，从而改变了多个机器人平台和环境的轨迹的形状和速度。这项研究迈出了建立机器人技术的大型预训练的基础模型的一步，并展示了这样的模型如何在人与机器之间建立更直观，更灵活的相互作用。代码库可在以下网址提供：https：//github.com/arthurfenderbucker/nl_traimptory_reshaper。

Transformer, originally devised for natural language processing, has also attested significant success in computer vision. Thanks to its super expressive power, researchers are investigating ways to deploy transformers to reinforcement learning (RL) and the transformer-based models have manifested their potential in representative RL benchmarks. In this paper, we collect and dissect recent advances on transforming RL by transformer (transformer-based RL or TRL), in order to explore its development trajectory and future trend. We group existing developments in two categories: architecture enhancement and trajectory optimization, and examine the main applications of TRL in robotic manipulation, text-based games, navigation and autonomous driving. For architecture enhancement, these methods consider how to apply the powerful transformer structure to RL problems under the traditional RL framework, which model agents and environments much more precisely than deep RL methods, but they are still limited by the inherent defects of traditional RL algorithms, such as bootstrapping and "deadly triad". For trajectory optimization, these methods treat RL problems as sequence modeling and train a joint state-action model over entire trajectories under the behavior cloning framework, which are able to extract policies from static datasets and fully use the long-sequence modeling capability of the transformer. Given these advancements, extensions and challenges in TRL are reviewed and proposals about future direction are discussed. We hope that this survey can provide a detailed introduction to TRL and motivate future research in this rapidly developing field.

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.

Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we refer to as Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens. In this report we describe the model and the data, and document the current capabilities of Gato.

Our situated environment is full of uncertainty and highly dynamic, thus hindering the widespread adoption of machine-led Intelligent Decision-Making (IDM) in real world scenarios. This means IDM should have the capability of continuously learning new skills and efficiently generalizing across wider applications. IDM benefits from any new approaches and theoretical breakthroughs that exhibit Artificial General Intelligence (AGI) breaking the barriers between tasks and applications. Recent research has well-examined neural architecture, Transformer, as a backbone foundation model and its generalization to various tasks, including computer vision, natural language processing, and reinforcement learning. We therefore argue that a foundation decision model (FDM) can be established by formulating various decision-making tasks as a sequence decoding task using the Transformer architecture; this would be a promising solution to advance the applications of IDM in more complex real world tasks. In this paper, we elaborate on how a foundation decision model improves the efficiency and generalization of IDM. We also discuss potential applications of a FDM in multi-agent game AI, production scheduling, and robotics tasks. Finally, through a case study, we demonstrate our realization of the FDM, DigitalBrain (DB1) with 1.2 billion parameters, which achieves human-level performance over 453 tasks, including text generation, images caption, video games playing, robotic control, and traveling salesman problems. As a foundation decision model, DB1 would be a baby step towards more autonomous and efficient real world IDM applications.

By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can solve specific downstream tasks either zero-shot or with small task-specific datasets to a high level of performance. While this capability has been demonstrated in other fields such as computer vision, natural language processing or speech recognition, it remains to be shown in robotics, where the generalization capabilities of the models are particularly critical due to the difficulty of collecting real-world robotic data. We argue that one of the keys to the success of such general robotic models lies with open-ended task-agnostic training, combined with high-capacity architectures that can absorb all of the diverse, robotic data. In this paper, we present a model class, dubbed Robotics Transformer, that exhibits promising scalable model properties. We verify our conclusions in a study of different model classes and their ability to generalize as a function of the data size, model size, and data diversity based on a large-scale data collection on real robots performing real-world tasks. The project's website and videos can be found at robotics-transformer.github.io

微调加强学习（RL）模型由于缺乏大规模的现成数据集以及不同环境之间可传递性的较高差异而变得具有挑战性。最近的工作着眼于从序列建模的角度来应对离线RL，并通过引入变压器体系结构的结果得到改进的结果。但是，当模型从头开始训练时，它会遭受缓慢的收敛速度。在本文中，我们希望利用这种强化学习作为序列建模的表述，并研究在离线RL任务（控制，游戏）上进行填充时，在其他领域（视觉，语言）上进行了预训练的序列模型的可传递性。为此，我们还提出了改善这些域之间传递的技术。结果表明，在各种环境上的收敛速度和奖励方面，表现出一致的性能，加速了3-6倍的训练，并使用Wikipedia-pretrenained and GPT2语言模型在各种任务中实现了最先进的绩效。我们希望这项工作不仅为RL利用通用序列建模技术和预训练模型的潜力带来启发，而且还激发了未来的工作，在完全不同领域的生成建模任务之间共享知识。

在人类环境中，预计在简单的自然语言指导下，机器人将完成各种操纵任务。然而，机器人的操纵极具挑战性，因为它需要精细颗粒的运动控制，长期记忆以及对以前看不见的任务和环境的概括。为了应对这些挑战，我们提出了一种基于统一的变压器方法，该方法考虑了多个输入。特别是，我们的变压器体系结构集成了（i）自然语言指示和（ii）多视图场景观察，而（iii）跟踪观察和动作的完整历史。这种方法使历史和指示之间的学习依赖性可以使用多个视图提高操纵精度。我们评估我们的方法在具有挑战性的RLBench基准和现实世界机器人方面。值得注意的是，我们的方法扩展到74个不同的RLBench任务，并超越了最新的现状。我们还解决了指导条件的任务，并证明了对以前看不见的变化的出色概括。

Current computer vision models, unlike the human visual system, cannot yet achieve general-purpose visual understanding. Existing efforts to create a general vision model are limited in the scope of assessed tasks and offer no overarching framework to perform them holistically. We present a new comprehensive benchmark, General-purpose Visual Understanding Evaluation (G-VUE), covering the full spectrum of visual cognitive abilities with four functional domains $\unicode{x2014}$ Perceive, Ground, Reason, and Act. The four domains are embodied in 11 carefully curated tasks, from 3D reconstruction to visual reasoning and manipulation. Along with the benchmark, we provide a general encoder-decoder framework to allow for the evaluation of arbitrary visual representation on all 11 tasks. We evaluate various pre-trained visual representations with our framework and observe that (1) Transformer-based visual backbone generally outperforms CNN-based backbone on G-VUE, (2) visual representations from vision-language pre-training are superior to those with vision-only pre-training across visual tasks. With G-VUE, we provide a holistic evaluation standard to motivate research toward building general-purpose visual systems via obtaining more general-purpose visual representations.

机器人技术中的一个长期目标是建立可以从使用其板载传感器获得的感知中执行各种日常任务的机器人，并且仅通过自然语言指定。尽管最近通过利用从像素的端到端学习来实现了在语言驱动的机器人技术中的实质性进步，但由于设置的基本差异，没有明确且妥善理解的过程来做出各种设计选择。在本文中，我们对从离线自由模仿数据集中学习语言条件政策的最关键挑战进行了广泛的研究。我们进一步确定了改善性能的架构和算法技术，例如机器人控制学习的层次分解，多模式变压器编码器，离散的潜在计划以及与视频和语言表示一致的自我监视的对比损失。通过将调查的结果与改进的模型组件相结合，我们能够提出一种新颖的方法，该方法在具有挑战性的语言条件长的长摩托器机器人操纵Calvin基准上大大优于最新技术。我们已经开源的实施方式，以促进未来的研究，以学习自然语言连续指定的许多复杂的操纵技能。 http://hulc.cs.uni-freiburg.de可用代码库和训练有素的模型

第一人称视频在其持续环境的背景下突出了摄影师的活动。但是，当前的视频理解方法是从短视频剪辑中的视觉特征的原因，这些视频片段与基础物理空间分离，只捕获直接看到的东西。我们提出了一种方法，该方法通过学习摄影师（潜在看不见的）本地环境来促进以人为中心的环境的了解来链接以自我为中心的视频和摄像机随着时间的推移而张开。我们使用来自模拟的3D环境中的代理商的视频进行训练，在该环境中，环境完全可以观察到，并在看不见的环境的房屋旅行的真实视频中对其进行测试。我们表明，通过将视频接地在其物理环境中，我们的模型超过了传统的场景分类模型，可以预测摄影师所处的哪个房间（其中帧级信息不足），并且可以利用这种基础来定位与环境相对应的视频瞬间 - 中心查询，优于先验方法。项目页面：http：//vision.cs.utexas.edu/projects/ego-scene-context/

从“Internet AI”的时代到“体现AI”的时代，AI算法和代理商出现了一个新兴范式转变，其中不再从主要来自Internet策划的图像，视频或文本的数据集。相反，他们通过与与人类类似的Enocentric感知来通过与其环境的互动学习。因此，对体现AI模拟器的需求存在大幅增长，以支持各种体现的AI研究任务。这种越来越多的体现AI兴趣是有利于对人工综合情报（AGI）的更大追求，但对这一领域并无一直存在当代和全面的调查。本文旨在向体现AI领域提供百科全书的调查，从其模拟器到其研究。通过使用我们提出的七种功能评估九个当前体现的AI模拟器，旨在了解模拟器，以其在体现AI研究和其局限性中使用。最后，本文调查了体现AI - 视觉探索，视觉导航和体现问题的三个主要研究任务（QA），涵盖了最先进的方法，评估指标和数据集。最后，随着通过测量该领域的新见解，本文将为仿真器 - 任务选择和建议提供关于该领域的未来方向的建议。

每个房屋都是不同的，每个人都喜欢以特殊方式完成的事情。因此，未来的家庭机器人需要既需要理由就日常任务的顺序性质，又要推广到用户的偏好。为此，我们提出了一个变压器任务计划者（TTP），该计划通过利用基于对象属性的表示来从演示中学习高级动作。TTP可以在多个偏好上进行预训练，并显示了使用单个演示作为模拟洗碗机加载任务中的提示的概括性的概括。此外，我们使用TTP与Franka Panda机器人臂一起展示了现实世界中的重排，并使用单一的人类示范引起了这种情况。

准确的本地化是大多数机器人任务的关键要求。现有工作的主体集中在被动定位上，其中假定了机器人的动作，从而从对抽样信息性观察的影响中抽象出来。尽管最近的工作表明学习动作的好处是消除机器人的姿势，但这些方法仅限于颗粒状的离散动作，直接取决于全球地图的大小。我们提出了主动粒子滤网网络（APFN），这种方法仅依赖于本地信息来进行可能的评估以及决策。为此，我们将可区分的粒子过滤器与加固学习剂进行了介绍，该材料会参与地图中最相关的部分。最终的方法继承了粒子过滤器的计算益处，并且可以直接在连续的动作空间中起作用，同时保持完全可区分，从而端到端优化以及对输入模式的不可知。我们通过在现实世界3D扫描公寓建造的影像现实主义室内环境中进行广泛的实验来证明我们的方法的好处。视频和代码可在http://apfn.cs.uni-freiburg.de上找到。

Humans are excellent at understanding language and vision to accomplish a wide range of tasks. In contrast, creating general instruction-following embodied agents remains a difficult challenge. Prior work that uses pure language-only models lack visual grounding, making it difficult to connect language instructions with visual observations. On the other hand, methods that use pre-trained vision-language models typically come with divided language and visual representations, requiring designing specialized network architecture to fuse them together. We propose a simple yet effective model for robots to solve instruction-following tasks in vision-based environments. Our \ours method consists of a multimodal transformer that encodes visual observations and language instructions, and a policy transformer that predicts actions based on encoded representations. The multimodal transformer is pre-trained on millions of image-text pairs and natural language text, thereby producing generic cross-modal representations of observations and instructions. The policy transformer keeps track of the full history of observations and actions, and predicts actions autoregressively. We show that this unified transformer model outperforms all state-of-the-art pre-trained or trained-from-scratch methods in both single-task and multi-task settings. Our model also shows better model scalability and generalization ability than prior work.

我们介绍了一个目标驱动的导航系统，以改善室内场景中的Fapless视觉导航。我们的方法在每次步骤中都将机器人和目标的多视图观察为输入，以提供将机器人移动到目标的一系列动作，而不依赖于运行时在运行时。通过优化包含三个关键设计的组合目标来了解该系统。首先，我们建议代理人在做出行动决定之前构建下一次观察。这是通过从专家演示中学习变分生成模块来实现的。然后，我们提出预测预先预测静态碰撞，作为辅助任务，以改善导航期间的安全性。此外，为了减轻终止动作预测的训练数据不平衡问题，我们还介绍了一个目标检查模块来区分与终止动作的增强导航策略。这三种建议的设计都有助于提高培训数据效率，静态冲突避免和导航泛化性能，从而产生了一种新颖的目标驱动的FLASES导航系统。通过对Turtlebot的实验，我们提供了证据表明我们的模型可以集成到机器人系统中并在现实世界中导航。视频和型号可以在补充材料中找到。

Developing robots that are capable of many skills and generalization to unseen scenarios requires progress on two fronts: efficient collection of large and diverse datasets, and training of high-capacity policies on the collected data. While large datasets have propelled progress in other fields like computer vision and natural language processing, collecting data of comparable scale is particularly challenging for physical systems like robotics. In this work, we propose a framework to bridge this gap and better scale up robot learning, under the lens of multi-task, multi-scene robot manipulation in kitchen environments. Our framework, named CACTI, has four stages that separately handle data collection, data augmentation, visual representation learning, and imitation policy training. In the CACTI framework, we highlight the benefit of adapting state-of-the-art models for image generation as part of the augmentation stage, and the significant improvement of training efficiency by using pretrained out-of-domain visual representations at the compression stage. Experimentally, we demonstrate that 1) on a real robot setup, CACTI enables efficient training of a single policy capable of 10 manipulation tasks involving kitchen objects, and robust to varying layouts of distractor objects; 2) in a simulated kitchen environment, CACTI trains a single policy on 18 semantic tasks across up to 50 layout variations per task. The simulation task benchmark and augmented datasets in both real and simulated environments will be released to facilitate future research.

A household robot should be able to navigate to target locations without requiring users to first annotate everything in their home. Current approaches to this object navigation challenge do not test on real robots and rely on expensive semantically labeled 3D meshes. In this work, our aim is an agent that builds self-supervised models of the world via exploration, the same as a child might. We propose an end-to-end self-supervised embodied agent that leverages exploration to train a semantic segmentation model of 3D objects, and uses those representations to learn an object navigation policy purely from self-labeled 3D meshes. The key insight is that embodied agents can leverage location consistency as a supervision signal - collecting images from different views/angles and applying contrastive learning to fine-tune a semantic segmentation model. In our experiments, we observe that our framework performs better than other self-supervised baselines and competitively with supervised baselines, in both simulation and when deployed in real houses.

感觉运动控制的强大范式是直接预测观察结果的动作。训练这样的端到端系统允许对下游任务有用的表示形式自动出现。在Visual Navigation中，代理可以通过将其视图与所采取的动作进行关联，而无需任何手动设计，就可以学会导航。但是，缺乏归纳偏见使得该系统在搜索和救援等场景中具有数据信息和不切实际，在这种情况下，与环境的互动以收集数据是昂贵的。我们假设当前视图的足够表示，可以通过预测与目标相对应的当前视图的作物的位置和大小来了解导航策略的目标视图。我们进一步表明，以自我监督的方式训练这种随机作物预测，纯粹是在随机噪声图像上很好地转移到自然家庭图像上。然后，可以通过很少的交互数据进行自动学习学习的表示形式，以有效地学习导航策略。代码可在https://github.com/yanweiw/noise2ptz上找到。