Related papers: ThinkBot: Embodied Instruction Following with Thou…
Given a natural language instruction and an input scene, our goal is to train a model to output a manipulation program that can be executed by the robot. Prior approaches for this task possess one of the following limitations: (i) rely on…
Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and…
Embodied navigation is a fundamental capability of embodied intelligence, enabling robots to move and interact within physical environments. However, existing navigation tasks primarily focus on predefined object navigation or instruction…
The ability to automatically learn movements and behaviors of increasing complexity is a long-term goal in autonomous systems. Indeed, this is a very complex problem that involves understanding how knowledge is acquired and reused by humans…
Embodied intelligence fundamentally requires a capability to determine where to act in 3D space. We formalize this requirement as embodied localization -- the problem of predicting executable 3D points conditioned on visual observations and…
In this paper, we argue that the future of Artificial Intelligence research resides in two keywords: integration and embodiment. We support this claim by analyzing the recent advances of the field. Regarding integration, we note that the…
Learning new skills by observing humans' behaviors is an essential capability of AI. In this work, we leverage instructional videos to study humans' decision-making processes, focusing on learning a model to plan goal-directed actions in…
The Instruction Following (IF) ability measures how well Multi-modal Large Language Models (MLLMs) understand exactly what users are telling them and whether they are doing it right. Existing multimodal instruction following training data…
An embodied task such as embodied question answering (EmbodiedQA), requires an agent to explore the environment and collect clues to answer a given question that related with specific objects in the scene. The solution of such task usually…
We present an embodied AI system which receives open-ended natural language instructions from a human, and controls two arms to collaboratively accomplish potentially long-horizon tasks over a large workspace. Our system is modular: it…
Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as…
Text-based games present a unique class of sequential decision making problem in which agents interact with a partially observable, simulated environment via actions and observations conveyed through natural language. Such observations…
Human-to-human conversation is not just talking and listening. It is an incremental process where participants continually establish a common understanding to rule out misunderstandings. Current language understanding methods for…
Vision-Language-Action (VLA) models leverage pretrained vision-language models (VLMs) to couple perception with robotic control, offering a promising path toward general-purpose embodied intelligence. However, current SOTA VLAs are…
Performing simple household tasks based on language directives is very natural to humans, yet it remains an open challenge for AI agents. The 'interactive instruction following' task attempts to make progress towards building agents that…
Endowing robots with the human ability to learn a growing set of skills over the course of a lifetime as opposed to mastering single tasks is an open problem in robot learning. While multi-task learning approaches have been proposed to…
Intelligent instruction-following robots capable of improving from autonomously collected experience have the potential to transform robot learning: instead of collecting costly teleoperated demonstration data, large-scale deployment of…
The study of human-robot interaction is fundamental to the design and use of robotics in real-world applications. Robots will need to predict and adapt to the actions of human collaborators in order to achieve good performance and improve…
We propose AToM-Bot, a novel task generation and execution framework for proactive robot-human interaction, which leverages the human mental and physical state inference capabilities of the Vision Language Model (VLM) prompted by the…
Humans can perform complex tasks with long-term objectives by planning, reasoning, and forecasting outcomes of actions. For embodied agents to achieve similar capabilities, they must gain knowledge of the environment transferable to novel…