Indoor service and inspection robots need environment knowledge that is queryable, reliable, and maintainable as the site changes, yet open-vocabulary 3D pipelines propagate unverified labels downstream and build-once scene models offer no maintenance path. We present TLS-SMF, a semantic modeling framework that converts registered terrestrial laser scans into a confidence-aware semantic knowledge graph and keeps it current across repeated scans. TLS-SMF combines (i) a deterministic geometric backbone whose re-runs are byte-identical on the same host, (ii) multi-view vision–language-model verification with automatic escalation that retains unresolved objects as explicitly unverified, and (iii) identity-preserving incremental updates that apply confidence-gated node-level upserts to mint-once node identities. Across two operational configurations of one industrial room, escalation lifts verification accuracy from 77.8% to 88.9% and from 78.1% to 84.4%, with 94.4–100% unanimous-vote precision against confirmed owner ground truth; on the showroom benchmark, structurally gated querying answers 83.3% of questions versus 52.1% for an unverified Stage-A LLM baseline while blocking hallucination traps; in a controlled same-quality combined-edit re-scan, selective re-verification reduces VLM cost to 3.1% of a full rebuild; and a real three-epoch study detects 2/2 controlled physical changes with zero observed identity switches on strong reference correspondences, while re-segmentation still produces false-new/false-absent cases. A cross-floor cafeteria stress scene bounds domain transfer, and an owner-in-the-loop revision path keeps the single semantic store corrigible for robot-facing use; the same store drives a physical mobile manipulator, which completes three console-issued semantic missions with a mean arrival error of 0.30 m while phantom goals are refused with zero motion.

Automated three-dimensional (3D) mapping with a survey-grade terrestrial laser scanner (TLS) is the canonical instance of robotic stop-and-scan light detection and ranging (LiDAR) mapping: the mobile platform must remain stationary for minutes per scan, so the environment must be covered with as few scans as possible. Where to stop hinges on a coverage model predicting what a scan pose will observe. The conventional isotropic-disk model counts every free cell within sensing range as covered—including cells behind walls—and, therefore, skips scans that genuine observation requires. We replace the disk with a ray-cast visibility region computed on the robot’s live two-dimensional (2D) occupancy map, admitting only cells in direct line of sight; define a line-of-sight (LOS) coverage metric over mapped free space and drive a marginal-gain scan/skip rule embedded in frontier exploration. The planner thus performs 2D scan-station placement for subsequent 3D mapping. In a controlled paired ablation in simulation, the visibility rule raises LOS coverage from about 77% to 84–85% for one to two additional scans, and it also outperforms a disk baseline governed by the identical marginal-gain rule, isolating the coverage model itself as the decisive factor. In a fully autonomous on-hardware comparison in an industrial test room, with each rule driving a mobile platform carrying a Leica BLK360 G1, the visibility rule raised LOS coverage from 77.6% to 92.1%; every visibility run’s scans registered offline at survey grade (4–5 mm bundle error, 84–88% overlap), whereas disk runs yielded at best a single-link network and once a single unregistrable scan. The results indicate that, for the room-scale indoor environments studied, occlusion-aware visibility is a sounder basis than Euclidean proximity for stop-and-scan placement.