We study the problem of learning a robot policy to follow natural language instructions that can be easily extended to reason about new objects. We introduce a few-shot language-conditioned object grounding method trained from augmented reality data that uses exemplars to identify objects and align them to their mentions in instructions. We present a learned map representation that encodes object locations and their instructed use, and construct it from our few-shot grounding output. We integrate this mapping approach into an instruction-following policy, thereby allowing it to reason about previously unseen objects at test-time by simply adding exemplars. We evaluate on the task of learning to map raw observations and instructions to continuous control of a physical quadcopter. Our approach significantly outperforms the prior state of the art in the presence of new objects, even when the prior approach observes all objects during training.
University of Manchester（曼彻斯特大学）；Blue Prism AI Labs（蓝棱镜人工智能实验室）；ByteDance AI Lab（字节跳动人工智能实验室）；Idiap Research Institute（Idiap研究所）
Models designed for intelligent process automation are required to be capable of grounding user interface elements. This task of interface element grounding is centred on linking instructions in natural language to their target referents. Even though BERT and similar pre-trained language models have excelled in several NLP tasks, their use has not been widely explored for the UI grounding domain. This work concentrates on testing and probing the grounding abilities of three different transformer-based models: BERT, RoBERTa and LayoutLM. Our primary focus is on these models' spatial reasoning s…
Spoken language is a convenient interface for commanding a mobile robot. Yet for this to work a number of base terms must be grounded in perceptual and motor skills. We detail the language processing used on our robot ELI and explain how this grounding is performed, how it interacts with user gestures, and how it handles phenomena such as anaphora. More importantly, however, there are certain concepts which the robot cannot be preprogrammed with, such as the names of various objects in a household or the nature of specific tasks it may be requested to perform. In these cases it is vital that t…
Embodied instruction following is a challenging problem requiring an agent to infer a sequence of primitive actions to achieve a goal environment state from complex language and visual inputs. Action Learning From Realistic Environments and Directives (ALFRED) is a recently proposed benchmark for this problem consisting of step-by-step natural language instructions to achieve subgoals which compose to an ultimate high-level goal. Key challenges for this task include localizing target locations and navigating to them through visual inputs, and grounding language instructions to visual appearanc…
Natural Human-Robot Interaction (HRI) is one of the key components for service robots to be able to work in human-centric environments. In such dynamic environments, the robot needs to understand the intention of the user to accomplish a task successfully. Towards addressing this point, we propose a software architecture that segments a target object from a crowded scene, indicated verbally by a human user. At the core of our system, we employ a multi-modal deep neural network for visual grounding. Unlike most grounding methods that tackle the challenge using pre-trained object detectors via a…
Human-robot interaction often occurs in the form of instructions given from a human to a robot. For a robot to successfully follow instructions, a common representation of the world and objects in it should be shared between humans and the robot so that the instructions can be grounded. Achieving this representation can be done via learning, where both the world representation and the language grounding are learned simultaneously. However, in robotics this can be a difficult task due to the cost and scarcity of data. In this paper, we tackle the problem by separately learning the world represe…
Instruction tuning is an emergent paradigm in NLP wherein natural language instructions are leveraged with language models to induce zero-shot performance on unseen tasks. Instructions have been shown to enable good performance on unseen tasks and datasets in both large and small language models. Dialogue is an especially interesting area to explore instruction tuning because dialogue systems perform multiple kinds of tasks related to language (e.g., natural language understanding and generation, domain-specific interaction), yet instruction tuning has not been systematically explored for dial…
One-Shot Learning as Instruction Data Prospector for Large Language Models
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Alibaba Group（阿里巴巴集团）；The University of Sydney（悉尼大学）
This paper explores a simple method for improving the zero-shot learning abilities of language models. We show that instruction tuning -- finetuning language models on a collection of tasks described via instructions -- substantially improves zero-shot performance on unseen tasks. We take a 137B parameter pretrained language model and instruction-tune it on over 60 NLP tasks verbalized via natural language instruction templates. We evaluate this instruction-tuned model, which we call FLAN, on unseen task types. FLAN substantially improves the performance of its unmodified counterpart and surpa…
Large Language Models are affected by the phenomena of memorizing and forgetting their training data. But how do these vary by model size? We work towards this question by investigating how the model size affects the model's ability to discriminate a word's meaning in a given context. We introduce a dataset called DeltaWords, which evaluates a model's ability to follow instructions to select a sentence which replaces the target word with its antonym. We show a weak inverse scaling trend, where task accuracy degrades as model size increase, under extremely few-shot prompting regimes. We show th…
Robots are widely collaborating with human users in diferent tasks that require high-level cognitive functions to make them able to discover the surrounding environment. A difcult challenge that we briefy highlight in this short paper is inferring the latent grammatical structure of language, which includes grounding parts of speech (e.g., verbs, nouns, adjectives, and prepositions) through visual perception, and induction of Combinatory Categorial Grammar (CCG) for phrases. This paves the way towards grounding phrases so as to make a robot able to understand human instructions appropriately d…
Tsinghua University（清华大学）；Institute for Artificial Intelligence（人工智能研究院）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Training language models to learn from human instructions for zero-shot cross-task generalization has attracted much attention in NLP communities. Recently, instruction tuning (IT), which fine-tunes a pre-trained language model on a massive collection of tasks described via human-craft instructions, has been shown effective in instruction learning for unseen tasks. However, IT relies on a large amount of human-annotated samples, which restricts its generalization. Unlike labeled data, unlabeled data are often massive and cheap to obtain. In this work, we study how IT can be improved with unlab…
We present a new method, PARsing And visual GrOuNding (ParaGon), for grounding natural language in object placement tasks. Natural language generally describes objects and spatial relations with compositionality and ambiguity, two major obstacles to effective language grounding. For compositionality, ParaGon parses a language instruction into an object-centric graph representation to ground objects individually. For ambiguity, ParaGon uses a novel particle-based graph neural network to reason about object placements with uncertainty. Essentially, ParaGon integrates a parsing algorithm into a p…
To perform tasks specified by natural language instructions, autonomous agents need to extract semantically meaningful representations of language and map it to visual elements and actions in the environment. This problem is called task-oriented language grounding. We propose an end-to-end trainable neural architecture for task-oriented language grounding in 3D environments which assumes no prior linguistic or perceptual knowledge and requires only raw pixels from the environment and the natural language instruction as input. The proposed model combines the image and text representations using…
University of Freiburg（弗赖堡大学）；Toyota Research Institute（丰田研究院）
Controlling robots to perform tasks via natural language is one of the most challenging topics in human-robot interaction. In this work, we present a robot system that follows unconstrained language instructions to pick and place arbitrary objects and effectively resolves ambiguities through dialogues. Our approach infers objects and their relationships from input images and language expressions and can place objects in accordance with the spatial relations expressed by the user. Unlike previous approaches, we consider grounding not only for the picking but also for the placement of everyday o…
OpenMap: Instruction Grounding via Open-Vocabulary Visual-Language Mapping
School of Software, Tsinghua University（清华大学软件学院）；School of computer science and engineering, Central South University（中南大学计算机科学与工程学院）；Inspur Yunzhou Industrial Internet Co., Ltd（Inspur Yunzhou工业互联网有限公司）；Tsinghua University（清华大学）
Transdisciplinary Institute of Medicine & Advanced Technology（医学与先进技术跨学科研究所）；Seoul National University（首尔国立大学）；German Aerospace Center (DLR)（德国航空航天中心）；Institute of Robotics and Mechatronics（机器人与机电一体化研究所）；Technical University of Munich（慕尼黑工业大学）
This paper emphasizes the importance of a robot's ability to refer to its task history, especially when it executes a series of pick-and-place manipulations by following language instructions given one by one. The advantage of referring to the manipulation history can be categorized into two folds: (1) the language instructions omitting details but using expressions referring to the past can be interpreted, and (2) the visual information of objects occluded by previous manipulations can be inferred. For this, we introduce a history-dependent manipulation task which objective is to visually gro…
We address one-shot imitation learning, where the goal is to execute a previously unseen task based on a single demonstration. While there has been exciting progress in this direction, most of the approaches still require a few hundred tasks for meta-training, which limits the scalability of the approaches. Our main contribution is to formulate one-shot imitation learning as a symbolic planning problem along with the symbol grounding problem. This formulation disentangles the policy execution from the inter-task generalization and leads to better data efficiency. The key technical challenge is…
VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding
The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Laboratory（上海人工智能实验室）；Zhejiang University（浙江大学）；Centre for Perceptual and Interactive Intelligence（感知与交互智能中心）
Instruction-Augmented Long-Horizon Planning: Embedding Grounding Mechanisms in Embodied Mobile Manipulation
The Hong Kong Polytechnic University（香港理工大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（东方理工大学宁波数字孪生研究院）；Great Bay University（大湾区大学）；Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
