Naming Objects for Vision-and-Language Manipulation

Robotics and Autonomous Systems

The utility of collocating robots largely depends on the easy and intuitive interaction mechanism with the human. If a robot accepts task instruction in natural language, first, it has to understand the user's intention by decoding the instruction. However, while executing the task, the robot may face unforeseeable circumstances due to the variations in the observed scene and therefore requires further user intervention. In this article, we present a system called Talk-to-Resolve (TTR) that enables a robot to initiate a coherent dialogue exchange with the instructor by observing the scene visually to resolve the impasse. Through dialogue, it either finds a cue to move forward in the original plan, an acceptable alternative of the original plan, or affirmation to abort the task altogether. To realize the possible stalemate, we utilize the dense captions of the observed scene and the given instruction jointly to compute the robot's next action. We evaluate our system based on a data set of initial instruction and situational scene pairs. Our system can identify the stalemate and resolve them with appropriate dialogue exchange with 82% accuracy. Additionally, a user study reveals that the questions from our systems are more natural (4.02 on average on a scale of 1 to 5) as compared to a state-of-the-art (3.08 on average).

Proceedings of the Twenty-first National Conference on …, 2006

2021 IEEE International Conference on Robotics and Automation (ICRA)

Robots that can manipulate objects in unstructured environments and collaborate with humans can benefit immensely by understanding natural language. We propose a pipelined architecture of two stages to perform spatial reasoning on the text input. All the objects in the scene are first localized, and then the instruction for the robot in natural language and the localized coordinates are mapped to the start and end coordinates corresponding to the locations where the robot must pick up and place the object respectively. We show that representing the localized objects by quantizing their positions to a binary grid is preferable to representing them as a list of 2D coordinates. We also show that attention improves generalization and can overcome biases in the dataset. The proposed method is used to pick-and-place playing cards using a robot arm.

arXiv (Cornell University), 2020

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 instructionfollowing 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.

Robot and Human Interactive …, 2002

2017

We present a cognitively plausible system capable of acquiring knowledge in language and vision from pairs of short video clips and linguistic descriptions. The aim of this work is to teach a robot manipulator how to execute natural language commands by demonstration. This is achieved by first learning a set of visual 'concepts' that abstract the visual feature spaces into concepts that have human-level meaning. Second, learning the mapping/grounding between words and the extracted visual concepts. Third, inducing grammar rules via a semantic representation known as Robot Control Language (RCL). We evaluate our approach against state-of-the-art supervised and unsupervised grounding and grammar induction systems, and show that a robot can learn to execute never seenbefore commands from pairs of unlabelled linguistic and visual inputs.

This paper presents a method to associate mean- ings to words in manipulation tasks. We base our model on an affordance network, i.e., a mapping between robot actions, robot perceptions and the perceived effects of these actions upon objects. This knowledge is acquired by the robot in an unsupervised way by self-interaction with the environment. When a human user is involved in the process and describes a particular task, the robot can form associations between the (co-occurrence of) speech utterances and the involved objects, actions and effects. We extend the affordance model to incorporate a simple description of speech as a set of words. We show that, across many experiences, the robot is able form useful word-to-meaning associations, even without considering grammatical structure in the learning process and in the presence of recognition errors. Word-to-meaning associations are then used to instruct the robot to perform tasks and also allow to incorporate context in the speech ...

Being able to quickly and naturally teach robots new knowledge is critical for many future open-world human-robot interaction scenarios. In this paper we present a novel approach to using natural language context for one-shot learning of visual objects, where the robot is immediately able to recognize the described object. We describe the architectural components and demonstrate the proposed method approach on a robotic platform in a proof-of-concept evaluation.

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

As the number of robots in our daily surroundings like home, office, restaurants, factory floors, etc. are increasing rapidly, the development of natural human-robot interaction mechanism becomes more vital as it dictates the usability and acceptability of the robots. One of the valued features of such a cohabitant robot is that it performs tasks that are instructed in natural language. However, it is not trivial to execute the human intended tasks as natural language expressions can have large linguistic variations. Existing works assume either single task instruction is given to the robot at a time or there are multiple independent tasks in an instruction. However, complex task instructions composed of multiple interdependent tasks are not handled efficiently in the literature. There can be ordering dependency among the tasks, i.e., the tasks have to be executed in a certain order or there can be execution dependency, i.e., input parameter or execution of a task depends on the outcome of another task. Understanding such dependencies in a complex instruction is not trivial if an unconstrained natural language is allowed. In this work, we propose a method to find the intended order of execution of multiple interdependent tasks given in natural language instruction. Based on our experiment, we show that our system is very accurate in generating a viable execution plan from a complex instruction.

2021

Enabling human operators to interact with robotic agents using natural 1 language would allow non-experts to intuitively instruct these agents. Towards 2 this goal, we propose a novel Transformer-based model which enables a user to 3 guide a robot arm through a 3D multi-step manipulation task with natural lan4 guage commands. Our system maps images and commands to masks over grasp 5 or place locations, grounding the language directly in perceptual space. In a suite 6 of block rearrangement tasks, we show that these masks can be combined with an 7 existing manipulation framework without re-training to greatly improve learning 8 efficiency. Our masking model performs well with just a few hundred real training 9 images, which is several orders of magnitude fewer examples than the millions of 10 examples typically required for training Transformer models. Our modular design 11 allows us to leverage supervised and reinforcement learning, providing an easy 12 interface for experimentation...