EgoWalk supplies 50 hours of real-world multimodal human navigation data in varied indoor/outdoor settings together with open pipelines that auto-generate language goal annotations and traversability masks.
Flownav: Combining flow matching and depth priors for efficient navigation
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3representative citing papers
RoamFlow applies MeanFlow to predict average velocity fields for one-step action policies in image-goal navigation, trained via expert imitation followed by RL refinement.
SEMNAV trains visual semantic navigation policies on semantic segmentation inputs rather than RGB, reports higher success rates in Habitat 2.0 on HM3D, and shows improved real-world transfer on robotic platforms.
citing papers explorer
-
EgoWalk: A Multimodal Dataset for Robot Navigation in the Wild
EgoWalk supplies 50 hours of real-world multimodal human navigation data in varied indoor/outdoor settings together with open pipelines that auto-generate language goal annotations and traversability masks.
-
RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation
RoamFlow applies MeanFlow to predict average velocity fields for one-step action policies in image-goal navigation, trained via expert imitation followed by RL refinement.
-
SEMNAV: Enhancing Visual Semantic Navigation in Robotics through Semantic Segmentation
SEMNAV trains visual semantic navigation policies on semantic segmentation inputs rather than RGB, reports higher success rates in Habitat 2.0 on HM3D, and shows improved real-world transfer on robotic platforms.