GlassGuard: Verified Glass Plane Mapping for Robot Navigation

Summary

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.

Abstract Summary

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/.

Key Points

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.

Problem Formulation

For robot navigation, glass reconstruction must satisfy two basic occupancy requirements: physical glass should be represented as occupied, while surrounding traversable space should remain free; these requirements motivate our problem formulation. Let $G_{t}\subset\mathbb{R}^{3}$ denote the true glass surfaces within the region observed by time $t$, and let $S_{t}$ contain all physical surfaces in that region.

Method

GlassGuard organizes detection as three stages in which each module contributes only what it is reliable for (Fig. 2 ). First , a quantized Slim SAM3 student detects glass-instance masks (Sec. IV-B ); each mask is associated with the surrounding LiDAR geometry to extract seed points (projected 3D points used to localize glass surfaces).

Selected seeds are then grouped into vertical and horizontal pillars, from which bounded 3D plane candidates are constructed (Sec. IV-C ).

Method — GlassGuard: Verified Glass Plane Mapping for Robot Navigation — Fig. 2: System overview; A–D mark four glass instances traced end to end. 1. Detect (left): Slim SAM3 Detection yields instance masks on the RGB panorama, each cropped to its Mask Frame ; Associate Masks with 3D projects the LiDAR cloud through that frame to obtain seeds, from which vertical and horizontal pillars and bounded plane candidates are built (Sec. IV-C ). 2. Verify Planes (center): Single-Frame Ray-Cast Verification checks each candidate against the depth-free 2D inferred orientation (Sec. IV-D ; crosses rejected, check accepted), and Multi-View Reprojection Verification removes a plane whose off-mask fraction grows as the robot moves. 3. Global Management (right): the Global Seed-Floor Evidence Map drives Floor Eviction , and Global Plane Merge and Absorb resolves overlapping hypotheses by seed count (Sec. IV-E ); surviving planes enter the navigation map.

Experiments

We evaluate GlassGuard and the baselines using a Mecanum-wheel robot equipped with a Livox Mid-360 LiDAR operating at $10$ Hz [ 1 ] and a $1920\times 640$ Ricoh Theta panoramic camera. At each frame, every LiDAR-using method receives the same $5$ s stack of registered point clouds together with synchronized RGB input.

The pinhole methods receive the same pinhole RGB view, while GG-360 receives the full $360^{\circ}$ panoramic image. GlassGuard runs onboard at a mean of approximately $0.74$ s per frame on an NVIDIA RTX 5070 Ti laptop GPU.

Experiments — GlassGuard: Verified Glass Plane Mapping for Robot Navigation — Fig. 3: Depth-free 2D$\to$3D verification. (a) A reliable silhouette edge anchors a support quadrilateral enclosing the observed glass mask; its boundary samples are back-projected as camera rays. (b) Opposite-side interpretation planes recover the pane’s in-plane directions and hence a depth-free reference orientation. (c) The resulting yaw reference is compared with the LiDAR-derived candidate; angular disagreement produces a false blockage that widens along the plane, motivating a length-dependent acceptance threshold.

Sources and Demonstrations

Figures are reproduced from Guo et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.