GlassGuard detects glass planes to improve robot navigation safety
GlassGuard: Verified Glass Plane Mapping for Robot Navigation
Robotics
Summary
Robots that use lasers to navigate often miss glass walls or doors because lasers can pass through glass without bouncing back, making maps incomplete and unsafe. The authors introduce GlassGuard, a method that combines camera images and laser data to identify and map glass surfaces as planes. This helps robots know where glass obstacles really are, avoiding collisions and keeping navigation paths clear. GlassGuard was tested in real buildings and improved glass detection while reducing map errors compared to previous methods.
What this means in practice
- •For robotics engineers: Improve indoor robot navigation by accurately mapping glass obstacles using combined visual and laser data.
- •For building automation teams: Enhance safety of autonomous robots in buildings by detecting transparent architectural features that are invisible to laser sensors.
Authors
Hanwen Guo, Zhengzhi Lin, Yusen Xie, Ji Zhang
Abstract
Transparent and specular surfaces pose a serious challenge to LiDAR-based SLAM and navigation because laser returns may pass through glass, leaving collision boundaries absent from the map. Prior work attempts to reconstruct the missing surfaces, but inaccurate obstacle placement can create the opposite failure: contamination of traversable free space. Recognizing this dual requirement, we present GlassGuard, a navigation-oriented framework for reconstructing planar architectural glass from complementary visual and LiDAR evidence. We formulate success in terms of both glass coverage and free-space contamination and apply this principle throughout proposal verification and global map construction. A foundation vision model provides glass-instance masks, structural 3D cues generate metric plane hypotheses, and depth-free 2D projective geometry checks their orientations before they enter a consolidated global map. We evaluate GlassGuard in nine building-scale scenes spanning diverse glass structures, spatial scales, and lighting conditions, with more than one hour and 2.1 km of real-world robot traversal. GlassGuard achieves 85% of total glass coverage for its panoramic version. Under identical pinhole inputs, GlassGuard achieves 82% total coverage, compared with at most 61% for the evaluated baselines, while producing 5-17x fewer false voxels per frame. Qualitative examples with a navigation planner illustrate the reconstructed planes blocking paths through glass while leaving traversable routes open. The project page is available at https://glassguardproject.github.io/.