Simple but effective: Clip embeddings for embodied ai
Contrastive language image pretraining (CLIP) encoders have been shown to be beneficial
for a range of visual tasks from classification and detection to captioning and image …
for a range of visual tasks from classification and detection to captioning and image …
Zson: Zero-shot object-goal navigation using multimodal goal embeddings
We present a scalable approach for learning open-world object-goal navigation (ObjectNav)–
the task of asking a virtual robot (agent) to find any instance of an object in an unexplored …
the task of asking a virtual robot (agent) to find any instance of an object in an unexplored …
Vlfm: Vision-language frontier maps for zero-shot semantic navigation
Understanding how humans leverage semantic knowledge to navigate unfamiliar
environments and decide where to explore next is pivotal for developing robots capable of …
environments and decide where to explore next is pivotal for developing robots capable of …
Learning navigational visual representations with semantic map supervision
Being able to perceive the semantics and the spatial structure of the environment is
essential for visual navigation of a household robot. However, most existing works only …
essential for visual navigation of a household robot. However, most existing works only …
3d-aware object goal navigation via simultaneous exploration and identification
Object goal navigation (ObjectNav) in unseen environments is a fundamental task for
Embodied AI. Agents in existing works learn ObjectNav policies based on 2D maps, scene …
Embodied AI. Agents in existing works learn ObjectNav policies based on 2D maps, scene …
Etpnav: Evolving topological planning for vision-language navigation in continuous environments
Vision-language navigation is a task that requires an agent to follow instructions to navigate
in environments. It becomes increasingly crucial in the field of embodied AI, with potential …
in environments. It becomes increasingly crucial in the field of embodied AI, with potential …
Object goal navigation with recursive implicit maps
Object goal navigation aims to navigate an agent to locations of a given object category in
unseen environments. Classical methods explicitly build maps of environments and require …
unseen environments. Classical methods explicitly build maps of environments and require …
Peanut: Predicting and navigating to unseen targets
Abstract Efficient ObjectGoal navigation (ObjectNav) in novel environments requires an
understanding of the spatial and semantic regularities in environment layouts. In this work …
understanding of the spatial and semantic regularities in environment layouts. In this work …
A survey of object goal navigation: Datasets, metrics and methods
Object Goal Navigation (ObjectNav) aims at directing an agent to a specified target object
within an unseen scene. This task integrates advanced techniques, including visual …
within an unseen scene. This task integrates advanced techniques, including visual …
Learning generalizable feature fields for mobile manipulation
An open problem in mobile manipulation is how to represent objects and scenes in a unified
manner, so that robots can use it both for navigating in the environment and manipulating …
manner, so that robots can use it both for navigating in the environment and manipulating …