Papers ObjectGoal Navigation
“ObjectGoal Navigation” 태그가 달린 논문 11편 · 필터 해제
TANGO: Training-free Embodied AI Agents for Open-world Tasks
Large Language Models (LLMs) have demonstrated excellent capabilities in composing various modules together to create programs that can perform complex reasoning tasks on images. In this paper, we propose TANGO, an appro…
Embodied Question AnsweringObjectGoal NavigationPointGoal NavigationQuestion AnsweringHabitat Synthetic Scenes Dataset (HSSD-200): An Analysis of 3D Scene Scale and Realism Tradeoffs for ObjectGoal Navigation
We contribute the Habitat Synthetic Scene Dataset, a dataset of 211 high-quality 3D scenes, and use it to test navigation agent generalization to realistic 3D environments. Our dataset represents real interiors and conta…
NavigateObjectGoal NavigationZero-shot GeneralizationPIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav
We study ObjectGoal Navigation -- where a virtual robot situated in a new environment is asked to navigate to an object. Prior work has shown that imitation learning (IL) using behavior cloning (BC) on a dataset of human…
Imitation LearningNavigateObjectGoal NavigationReinforcement Learning (RL)PEANUT: Predicting and Navigating to Unseen Targets
Efficient ObjectGoal navigation (ObjectNav) in novel environments requires an understanding of the spatial and semantic regularities in environment layouts. In this work, we present a straightforward method for learning …
ObjectGoal NavigationPredictionVER: Scaling On-Policy RL Leads to the Emergence of Navigation in Embodied Rearrangement
We present Variable Experience Rollout (VER), a technique for efficiently scaling batched on-policy reinforcement learning in heterogenous environments (where different environments take vastly different times to generat…
GPUNavigateObjectGoal NavigationOut-of-Distribution Generalization+1Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale
We present a large-scale study of imitating human demonstrations on tasks that require a virtual robot to search for objects in new environments -- (1) ObjectGoal Navigation (e.g. 'find & go to a chair') and (2) Pick&Pla…
Imitation LearningObjectGoal NavigationReinforcement Learning (RL)PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning
State-of-the-art approaches to ObjectGoal navigation rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Potential functions for ObjectGoal Navigatio…
NavigateObjectGoal NavigationAuxiliary Tasks and Exploration Enable ObjectNav
ObjectGoal Navigation (ObjectNav) is an embodied task wherein agents are to navigate to an object instance in an unseen environment. Prior works have shown that end-to-end ObjectNav agents that use vanilla visual and rec…
Auxiliary LearningNavigateObjectGoal NavigationRobot NavigationTHDA: Treasure Hunt Data Augmentation for Semantic Navigation
Can general-purpose neural models learn to navigate? For PointGoal navigation (""go to x, y""), the answer is a clear `yes' -- mapless neural models composed of task-agnostic components (CNNs and RNNs) trained with l…
Data AugmentationNavigateObjectGoal NavigationOpen-Ended Question Answering+1Auxiliary Tasks and Exploration Enable ObjectGoal Navigation
ObjectGoal Navigation (ObjectNav) is an embodied task wherein agents are to navigate to an object instance in an unseen environment. Prior works have shown that end-to-end ObjectNav agents that use vanilla visual and…
Auxiliary LearningNavigateObjectGoal NavigationMultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
Navigation tasks in photorealistic 3D environments are challenging because they require perception and effective planning under partial observability. Recent work shows that map-like memory is useful for long-horizon nav…
BenchmarkingObjectObjectGoal Navigation