Self-supervised model detects humans and estimates 2D pose from 1D LiDAR using RGB-D supervision, reporting 71% precision and 80% recall on unseen environments after 70 minutes of autonomous data collection.
Learning long-range perception using self-supervision from short-range sensors and odometry
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sixth-Sense: Self-Supervised Learning of Spatial Awareness of Humans from a Planar Lidar
Self-supervised model detects humans and estimates 2D pose from 1D LiDAR using RGB-D supervision, reporting 71% precision and 80% recall on unseen environments after 70 minutes of autonomous data collection.