相关论文: NeoNav: Improving the Generalization of Visual Nav…

We present a target-driven navigation system to improve mapless visual navigation in indoor scenes. Our method takes a multi-view observation of a robot and a target as inputs at each time step to provide a sequence of actions that move the…

Vision-Language Navigation requires the agent to follow natural language instructions to reach a specific target. The large discrepancy between seen and unseen environments makes it challenging for the agent to generalize well. Previous…

A multi-modal framework to generate user intention distributions when operating a mobile vehicle is proposed in this work. The model learns from past observed trajectories and leverages traversability information derived from the visual…

Existing vision-and-language navigation (VLN) models primarily reason over past and current visual observations, while largely ignoring the future visual dynamics induced by actions. As a result, they often lack an effective understanding…

It is crucial to ask how agents can achieve goals by generating action plans using only partial models of the world acquired through habituated sensory-motor experiences. Although many existing robotics studies use a forward model…

Vision transformer networks have shown superiority in many computer vision tasks. In this paper, we take a step further by proposing a novel generative vision transformer with latent variables following an informative energy-based prior for…

The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…

One powerful paradigm in visual navigation is to predict actions from observations directly. Training such an end-to-end system allows representations useful for downstream tasks to emerge automatically. However, the lack of inductive bias…

Vision-language Navigation (VLN) tasks require an agent to navigate step-by-step while perceiving the visual observations and comprehending a natural language instruction. Large data bias, which is caused by the disparity ratio between the…

Visual navigation requires agents to reach goals in complex environments through perception and planning. World models address this task by simulating action-conditioned state transitions to predict future observations. Current navigation…

We address tracking and prediction of multiple moving objects in visual data streams as inference and sampling in a disentangled latent state-space model. By encoding objects separately and including explicit position information in the…

Vision-and-Language Navigation (VLN) is the task that requires an agent to navigate through the environment based on natural language instructions. At each step, the agent takes the next action by selecting from a set of navigable…

We are motivated by the problem of learning policies for robotic systems with rich sensory inputs (e.g., vision) in a manner that allows us to guarantee generalization to environments unseen during training. We provide a framework for…

Visual perception and navigation have emerged as major focus areas in the field of embodied artificial intelligence. We consider the task of image-goal navigation, where an agent is tasked to navigate to a goal specified by an image,…

Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper,…

Most existing works in vision-and-language navigation (VLN) focus on either discrete or continuous environments, training agents that cannot generalize across the two. The fundamental difference between the two setups is that discrete…

Image-goal navigation aims to steer an agent towards the goal location specified by an image. Most prior methods tackle this task by learning a navigation policy, which extracts visual features of goal and observation images, compares their…

Image-goal navigation is a challenging task, as it requires the agent to navigate to a target indicated by an image in a previously unseen scene. Current methods introduce diverse memory mechanisms which save navigation history to solve…

Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future visual observations based on past observations and…

Embodied navigation in open, dynamic environments demands accurate foresight of how the world will evolve and how actions will unfold over time. We propose AstraNav-World, an end-to-end world model that jointly reasons about future visual…