In this work, we study the problem of Embodied Referring Expression Grounding, where an agent needs to navigate in a previously unseen environment and localize a remote object described by a concise high-level natural language instruction. When facing such a situation, a human tends to imagine what the destination may look like and to explore the environment based on prior knowledge of the environmental layout, such as the fact that a bathroom is more likely to be found near a bedroom than a kitchen. We have designed an autonomous agent called Layout-aware Dreamer (LAD), including two novel modules, that is, the Layout Learner and the Goal Dreamer to mimic this cognitive decision process. The Layout Learner learns to infer the room category distribution of neighboring unexplored areas along the path for coarse layout estimation, which effectively introduces layout common sense of room-to-room transitions to our agent. To learn an effective exploration of the environment, the Goal Dreamer imagines the destination beforehand. Our agent achieves new state-of-the-art performance on the public leaderboard of the REVERIE dataset in challenging unseen test environments with improvement in navigation success (SR) by 4.02% and remote grounding success (RGS) by 3.43% compared to the previous state-of-the-art. The code is released at https://github.com/zehao-wang/LAD
translated by 谷歌翻译
在视觉和语言导航(VLN)中,按照自然语言指令在现实的3D环境中需要具体的代理。现有VLN方法的一个主要瓶颈是缺乏足够的培训数据,从而导致对看不见的环境的概括不令人满意。虽然通常会手动收集VLN数据,但这种方法很昂贵,并且可以防止可扩展性。在这项工作中,我们通过建议从HM3D自动创建900个未标记的3D建筑物的大规模VLN数据集来解决数据稀缺问题。我们为每个建筑物生成一个导航图,并通过交叉视图一致性从2D传输对象预测,从2D传输伪3D对象标签。然后,我们使用伪对象标签来微调一个预处理的语言模型,作为减轻教学生成中跨模式差距的提示。在导航环境和说明方面,我们生成的HM3D-AUTOVLN数据集是比现有VLN数据集大的数量级。我们通过实验表明,HM3D-AUTOVLN显着提高了所得VLN模型的概括能力。在SPL指标上,我们的方法分别在Reverie和DataSet的看不见的验证分裂分别对艺术的状态提高了7.1%和8.1%。
translated by 谷歌翻译
Existing approaches for vision-and-language navigation (VLN) are mainly based on cross-modal reasoning over discrete views. However, this scheme may hamper an agent's spatial and numerical reasoning because of incomplete objects within a single view and duplicate observations across views. A potential solution is mapping discrete views into a unified birds's-eye view, which can aggregate partial and duplicate observations. Existing metric maps could achieve this goal, but they suffer from less expressive semantics (e.g. usually predefined labels) and limited map size, which weakens an agent's language grounding and long-term planning ability. Inspired by the robotics community, we introduce hybrid topo-metric maps into VLN, where a topological map is used for long-term planning and a metric map for short-term reasoning. Beyond mapping with more expressive deep features, we further design a pre-training framework via the hybrid map to learn language-informed map representations, which enhances cross-modal grounding and facilitates the final language-guided navigation goal. Extensive experiments demonstrate the effectiveness of the map-based route for VLN, and the proposed method sets the new state-of-the-art on three VLN benchmarks.
translated by 谷歌翻译
了解空间和视觉信息对于遵循自然语言说明的导航代理至关重要。当前的基于变压器的VLN代理纠缠了方向和视觉信息,这限制了每个信息源的学习中的增益。在本文中,我们设计了具有明确取向和视觉模块的神经药物。这些模块学会了将空间信息和地标在视觉环境中的说明中提及。为了加强代理的空间推理和视觉感知,我们设计了特定的预训练任务,以进食并更好地利用我们最终导航模型中的相应模块。我们在Room2Room(R2R)和Room4Room(R4R)数据集上评估我们的方法,并在两个基准测试中实现最新结果。
translated by 谷歌翻译
在本文中,我们介绍了地图语言导航任务,代理在其中执行自然语言指令,并仅基于给定的3D语义图移至目标位置。为了解决任务,我们设计了指导感的路径建议和歧视模型(IPPD)。我们的方法利用MAP信息来提供指导感知的路径建议,即,它选择所有潜在的指令一致的候选路径以减少解决方案空间。接下来,为表示沿路径的地图观测值以获得更好的模态对准,提出了针对语义图定制的新型路径特征编码方案。基于注意力的语言驱动的歧视者旨在评估候选路径,并确定最佳路径作为最终结果。与单步贪婪决策方法相比,我们的方法自然可以避免误差积累。与单步仿制学习方法相比,IPPD在导航成功方面的性能增长超过17%,而在有挑战性的看不见的环境中,在路径匹配测量NDTW上的性能增长了0.18。
translated by 谷歌翻译
Recent studies in Vision-and-Language Navigation (VLN) train RL agents to execute natural-language navigation instructions in photorealistic environments, as a step towards robots that can follow human instructions. However, given the scarcity of human instruction data and limited diversity in the training environments, these agents still struggle with complex language grounding and spatial language understanding. Pretraining on large text and image-text datasets from the web has been extensively explored but the improvements are limited. We investigate large-scale augmentation with synthetic instructions. We take 500+ indoor environments captured in densely-sampled 360 degree panoramas, construct navigation trajectories through these panoramas, and generate a visually-grounded instruction for each trajectory using Marky, a high-quality multilingual navigation instruction generator. We also synthesize image observations from novel viewpoints using an image-to-image GAN. The resulting dataset of 4.2M instruction-trajectory pairs is two orders of magnitude larger than existing human-annotated datasets, and contains a wider variety of environments and viewpoints. To efficiently leverage data at this scale, we train a simple transformer agent with imitation learning. On the challenging RxR dataset, our approach outperforms all existing RL agents, improving the state-of-the-art NDTW from 71.1 to 79.1 in seen environments, and from 64.6 to 66.8 in unseen test environments. Our work points to a new path to improving instruction-following agents, emphasizing large-scale imitation learning and the development of synthetic instruction generation capabilities.
translated by 谷歌翻译
我们研究了开发自主代理的问题,这些自主代理可以遵循人类的指示来推断和执行一系列行动以完成基础任务。近年来取得了重大进展,尤其是对于短范围的任务。但是,当涉及具有扩展动作序列的长匹马任务时,代理可以轻松忽略某些指令或陷入长长指令中间,并最终使任务失败。为了应对这一挑战,我们提出了一个基于模型的里程碑的任务跟踪器(M-Track),以指导代理商并监视其进度。具体而言,我们提出了一个里程碑构建器,该建筑商通过导航和交互里程碑标记指令,代理商需要逐步完成,以及一个系统地检查代理商当前里程碑的进度并确定何时继续进行下一个的里程碑检查器。在具有挑战性的Alfred数据集上,我们的M轨道在两个竞争基本模型中,未见成功率的相对成功率显着提高了33%和52%。
translated by 谷歌翻译
视觉和语言导航(VLN)任务要求代理根据语言说明浏览环境。在本文中,我们旨在解决此任务中的两个关键挑战:利用多语言指令改进教学路径接地,并在培训期间看不见的新环境中导航。为了应对这些挑战,我们提出了明确的:跨语性和环境不可屈服的表示。首先,我们的经纪人在室内室内数据集中学习了三种语言(英语,印地语和泰卢固语)的共享且视觉上的跨语言表示。我们的语言表示学习是由视觉信息对齐的文本对指导的。其次,我们的代理商通过从不同环境中最大化语义对齐的图像对(对象匹配的约束)之间的相似性来学习环境不足的视觉表示。我们的环境不可知的视觉表示可以减轻低级视觉信息引起的环境偏见。从经验上讲,在房间 - 室内数据集中,我们表明,当通过跨语性语言表示和环境 - 非局部视觉表示形式概括地看不见的环境时,我们的多语言代理在所有指标上都比强大的基线模型进行了巨大改进。此外,我们表明我们学到的语言和视觉表示可以成功地转移到房间和合作的视觉和二元式导航任务上,并提出详细的定性和定量的概括和基础分析。我们的代码可从https://github.com/jialuli-luka/clear获得
translated by 谷歌翻译
视觉和语言导航(VLN)是一种任务,即遵循语言指令以导航到目标位置的语言指令,这依赖于在移动期间与环境的持续交互。最近的基于变压器的VLN方法取得了很大的进步,从视觉观测和语言指令之间的直接连接通过多模式跨关注机制。然而,这些方法通常代表通过使用LSTM解码器或使用手动设计隐藏状态来构建反复变压器的时间上下文作为固定长度矢量。考虑到单个固定长度向量通常不足以捕获长期时间上下文,在本文中,我们通过显式建模时间上下文来引入具有可变长度存储器(MTVM)的多模式变压器,通过模拟时间上下文。具体地,MTVM使代理能够通过直接存储在存储体中的先前激活来跟踪导航轨迹。为了进一步提高性能,我们提出了内存感知的一致性损失,以帮助学习随机屏蔽指令的时间上下文的更好关节表示。我们在流行的R2R和CVDN数据集上评估MTVM,我们的模型在R2R看不见的验证和测试中提高了2%的成功率,并在CVDN测试集上减少了1.6米的目标进程。
translated by 谷歌翻译
Household environments are visually diverse. Embodied agents performing Vision-and-Language Navigation (VLN) in the wild must be able to handle this diversity, while also following arbitrary language instructions. Recently, Vision-Language models like CLIP have shown great performance on the task of zero-shot object recognition. In this work, we ask if these models are also capable of zero-shot language grounding. In particular, we utilize CLIP to tackle the novel problem of zero-shot VLN using natural language referring expressions that describe target objects, in contrast to past work that used simple language templates describing object classes. We examine CLIP's capability in making sequential navigational decisions without any dataset-specific finetuning, and study how it influences the path that an agent takes. Our results on the coarse-grained instruction following task of REVERIE demonstrate the navigational capability of CLIP, surpassing the supervised baseline in terms of both success rate (SR) and success weighted by path length (SPL). More importantly, we quantitatively show that our CLIP-based zero-shot approach generalizes better to show consistent performance across environments when compared to SOTA, fully supervised learning approaches when evaluated via Relative Change in Success (RCS).
translated by 谷歌翻译
建立一个对话体现的代理执行现实生活任务一直是一个长期而又具有挑战性的研究目标,因为它需要有效的人类代理沟通,多模式理解,远程顺序决策等。传统的符号方法具有扩展和概括问题,而端到端的深度学习模型则遭受数据稀缺和高任务复杂性的影响,并且通常很难解释。为了从两全其美的世界中受益,我们提出了一个神经符号常识性推理(JARVIS)框架,用于模块化,可推广和可解释的对话体现的药物。首先,它通过提示大型语言模型(LLM)来获得符号表示,以了解语言理解和次目标计划,并通过从视觉观察中构建语义图。然后,基于任务和动作级别的常识,次目标计划和行动生成的符号模块。在Teach数据集上进行的大量实验验证了我们的JARVIS框架的功效和效率,该框架在所有三个基于对话框的具体任务上实现了最新的(SOTA)结果,包括对话记录(EDH)的执行,对话框的轨迹, (TFD)和两个代理任务完成(TATC)(例如,我们的方法将EDH看不见的成功率从6.1 \%\%提高到15.8 \%)。此外,我们系统地分析了影响任务绩效的基本因素,并在几个射击设置中证明了我们方法的优越性。我们的Jarvis模型在Alexa奖Simbot公共基准挑战赛中排名第一。
translated by 谷歌翻译
视觉导航要求代理商遵循自然语言说明以达到特定目标。可见的环境和看不见的环境之间的巨大差异使代理商概括良好的挑战。先前的研究提出了数据增强方法,以明确或隐式地减轻数据偏见并提供概括的改进。但是,他们试图记住增强的轨迹,并在测试时忽略在看不见的环境下的分布变化。在本文中,我们提出了一个看不见的差异,预期视力和语言导航(戴维斯),该差异通过鼓励测试时间的视觉一致性来概括为看不见的环境。具体来说,我们设计了:1)半监督框架戴维斯(Davis),该框架利用类似的语义观测来利用视觉一致性信号。 2)一个两阶段的学习程序,鼓励适应测试时间分布。该框架增强了模仿和强化学习的基本混合物与动量形成对比,以鼓励在联合训练阶段和测试时间适应阶段对类似观察的稳定决策。广泛的实验表明,戴维斯在R2R和RXR基准上实现了与先前最先进的VLN基线相比,取得了模型不合命源性的改进。我们的源代码和数据是补充材料。
translated by 谷歌翻译
表演家庭和办公室任务的语言引导机器人必须导航和与世界互动。接地语言指示视觉观察和携带环境的行动是一个开放的挑战。我们呈现体现伯尔特(Embert),一种基于变压器的模型,可以参加跨长时间视野的高维,多模态输入进行语言条件任务完成。此外,我们通过引入Embert培训的对象导航目标来介绍用于非交互式代理的成功对象的导航模型和用于非交互式代理和语言引导的视觉任务完成基准。我们在Alfred基准测试中实现了竞争性能,eMbert标志着一个基于一个基于变压器的模型,以成功处理Alfred的长地平线,密集,多模态历史,以及使用以对象为中心的导航目标的第一个Alfred模型。
translated by 谷歌翻译
旨在为通用机器人铺平道路的边界研究,视觉和语言导航(VLN)一直是计算机视觉和自然语言处理社区的热门话题。 VLN任务要求代理在不熟悉的环境中按照自然语言说明导航到目标位置。最近,基于变压器的模型已在VLN任务上获得了重大改进。由于变压器体系结构中的注意力机制可以更好地整合视觉和语言的模式内和模式信息。但是,当前基于变压器的模型中存在两个问题。 1)模型独立处理每个视图,而无需考虑对象的完整性。 2)在视觉模态的自我注意操作期间,在空间上遥远的视图可以彼此交织而无需明确的限制。这种混合可能会引入额外的噪音而不是有用的信息。为了解决这些问题,我们建议1)基于插槽注意的模块,以合并来自同一对象的分割的信息。 2)局部注意力掩模机制限制视觉注意力跨度。所提出的模块可以轻松地插入任何VLN体系结构中,我们将复发的VLN-Bert用作基本模型。 R2R数据集的实验表明,我们的模型已达到最新结果。
translated by 谷歌翻译
视觉语言导航(VLN)任务要求代理商通过自然语言指令的指导到达目标。以前的作品学会在指令后逐步导航。然而,这些作品可能无法歧视跨指令轨迹对的相似性和差异,并忽略子指令的时间连续性。这些问题妨碍了代理人学习独特的视觉和语言表示,损害了导航政策的稳健性和普遍性。在本文中,我们提出了一种对比的指令轨迹学习(Citl)框架,探讨了不同数据样本的不变性,而不同的数据样本和方差以学习强大导航的独特表示。具体而言,我们提出:(1)通过分别对比完整轨迹观测和指示的语义来提高视觉和语言表示来提高视觉和语言。 (2)细粒度对比学学习目的,通过利用子指示的时间信息来感知指示; (3)对矿井硬样品对比学学习的成对采样重量机制,从而减轻了数据采样偏差在对比学习中的影响。我们的Citl可以轻松地与VLN骨干网集成,形成新的学习范例,并在看不见的环境中实现更好的普遍性。广泛的实验表明,Citl的模型超越了R2R,R4R和RXR上以前的最先进的方法。
translated by 谷歌翻译
Generalisation to unseen contexts remains a challenge for embodied navigation agents. In the context of semantic audio-visual navigation (SAVi) tasks, the notion of generalisation should include both generalising to unseen indoor visual scenes as well as generalising to unheard sounding objects. However, previous SAVi task definitions do not include evaluation conditions on truly novel sounding objects, resorting instead to evaluating agents on unheard sound clips of known objects; meanwhile, previous SAVi methods do not include explicit mechanisms for incorporating domain knowledge about object and region semantics. These weaknesses limit the development and assessment of models' abilities to generalise their learned experience. In this work, we introduce the use of knowledge-driven scene priors in the semantic audio-visual embodied navigation task: we combine semantic information from our novel knowledge graph that encodes object-region relations, spatial knowledge from dual Graph Encoder Networks, and background knowledge from a series of pre-training tasks -- all within a reinforcement learning framework for audio-visual navigation. We also define a new audio-visual navigation sub-task, where agents are evaluated on novel sounding objects, as opposed to unheard clips of known objects. We show improvements over strong baselines in generalisation to unseen regions and novel sounding objects, within the Habitat-Matterport3D simulation environment, under the SoundSpaces task.
translated by 谷歌翻译
This study focuses on embodied agents that can follow natural language instructions to complete complex tasks in a visually-perceived environment. Existing methods rely on a large amount of (instruction, gold trajectory) pairs to learn a good policy. The high data cost and poor sample efficiency prevents the development of versatile agents that are capable of many tasks and can learn new tasks quickly. In this work, we propose a novel method, LLM-Planner, that harnesses the power of large language models (LLMs) such as GPT-3 to do few-shot planning for embodied agents. We further propose a simple but effective way to enhance LLMs with physical grounding to generate plans that are grounded in the current environment. Experiments on the ALFRED dataset show that our method can achieve very competitive few-shot performance, even outperforming several recent baselines that are trained using the full training data despite using less than 0.5% of paired training data. Existing methods can barely complete any task successfully under the same few-shot setting. Our work opens the door for developing versatile and sample-efficient embodied agents that can quickly learn many tasks.
translated by 谷歌翻译
视觉室内导航(VIN)任务已从数据驱动的机器学习社区中引起了人们的关注,尤其是在最近报告的基于学习方法的成功中。由于这项任务的先天复杂性,研究人员尝试从各种不同角度解决问题,其全部范围尚未在总体报告中捕获。这项调查首先总结了VIN任务的基于学习的方法的代表性工作,然后确定并讨论了阻碍VIN绩效的问题,并激发了值得探索社区的这些关键领域的未来研究。
translated by 谷歌翻译
对象导航任务要求代理根据视觉信息在未知环境中找到特定对象。以前,图形卷积被用于隐式探索对象之间的关系。但是,由于对象之间可见性的差异,很容易在对象注意中产生偏见。因此,在本文中,我们提出了一个定向的对象注意(DOA)图,以指导代理显式地学习对象之间的注意力关系,从而减少对象的注意偏置。特别是,我们使用DOA图在原始图像上分别对对象特征和无偏的自适应图像注意(UAIA)进行无偏的自适应对象注意(UAOA)。为了区分不同分支的特征,提出了一种简洁的自适应分支分布(ABED)方法。我们在AI2-数据集上评估我们的方法。与最先进的方法(SOTA)方法相比,我们的方法报告了7.4%,8.1%和17.6%的成功率(SR),成功按路径长度(SPL)加权(SPL)并通过动作效率加权成功(SAE) ), 分别。
translated by 谷歌翻译
我们介绍了泰德(Tidee),这是一种体现的代理,它根据学识渊博的常识对象和房间安排先验来整理一个无序场景。泰德(Tidee)探索家庭环境,检测到其自然位置的对象,渗透到它们的合理对象上下文,在当前场景中定位此类上下文,并重新定位对象。常识先验在三个模块中编码:i)检测到现象对象的视觉声音检测器,ii)对象和空间关系的关联神经图记忆,提出了对象重新定位的合理语义插座和表面,以及iii)引导代理商探索的可视搜索网络,以有效地将利益定位在当前场景中以重新定位对象。我们测试了在AI2THOR模拟环境中整理混乱的场景的潮汐。 Tidee直接从像素和原始深度输入中执行任务,而没有事先观察到同一房间,仅依靠从单独的一组培训房屋中学到的先验。人类对由此产生的房间进行重组的评估表明,泰德(Tidee)的表现优于该模型的消融版本,这些版本不使用一个或多个常识性先验。在相关的房间重新安排基准测试中,该基准使代理可以在重新排列前查看目标状态,我们的模型的简化版本大大胜过了最佳的方法,可以通过大幅度的差距。代码和数据可在项目网站上获得:https://tidee-agent.github.io/。
translated by 谷歌翻译