SOTAVerified

PointGoal Navigation

Point goal navigation is a task where an agent navigates to a specific location, defined by coordinates (x, y), in an environment using sensory inputs like vision or depth, without a pre-built map, relying on real-time perception and decision-making.

Papers

Showing 1120 of 25 papers

TitleStatusHype
Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge0
Realistic PointGoal Navigation via Auxiliary Losses and Information BottleneckCode0
Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AICode1
The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation0
Out of the Box: Embodied Navigation in the Real WorldCode1
GridToPix: Training Embodied Agents with Minimal Supervision0
Large Batch Simulation for Deep Reinforcement LearningCode1
THDA: Treasure Hunt Data Augmentation for Semantic Navigation0
How to Train PointGoal Navigation Agents on a (Sample and Compute) Budget0
Auxiliary Tasks Speed Up Learning PointGoal NavigationCode1
Show:102550
← PrevPage 2 of 3Next →

No leaderboard results yet.