IndoorBEV: A Lightweight Real-Time LiDAR BEV Perception System
Overview
IndoorBEV is a lightweight LiDAR perception framework for indoor robots, using height-aware BEV and geometry-conditioned fusion for efficient real-time perception.
Generated from attributed reports · 2 days agoUpdated
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · parameters: 0.6 other · Basis not reported
“IndoorBEV contains only 0.6M parameters and requires 2.3 MB of model storage.”
Exact source · revision 1Source owner not reported
Reported quantity · model storage: 2.3 other · Basis not reported
“IndoorBEV contains only 0.6M parameters and requires 2.3 MB of model storage.”
Exact source · revision 1Source owner not reported
Reported quantity · GPU memory: 21.52 other · Basis not reported
“IndoorBEV contains only 0.6M parameters and requires 2.3 MB of model storage.”
Exact source · revision 1Source owner not reported
Reported quantity · latency: 169.6 other · Basis not reported
“IndoorBEV contains only 0.6M parameters and requires 2.3 MB of model storage.”
Exact source · revision 1Source owner not reported
Reported quantity · deadline miss ratio: 1.8 percent · Basis not reported
“IndoorBEV contains only 0.6M parameters and requires 2.3 MB of model storage.”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsIndoorBEV: A Lightweight Real-Time LiDAR BEV Perception System for Indoor Mobile Robots
IndoorBEV is a lightweight LiDAR perception framework that addresses the challenge of efficient indoor perception by integrating height-aware BEV representations and geometry-conditioned feature fusion. It achieves 0.6M parameters, 2.3 MB storage, and 169.6 ms latency on an NVIDIA AGX Orin, with a 1.8% deadline miss ratio.
Event attention history
Current attention 3·Peak within the comparable range 9（2026-10-02 06:00 UTC）·Change within the comparable range over 24 hours -49%
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.