🤖 AI Summary
This study addresses the ambiguity in exploratory navigation caused by purely geometric predictive maps, which struggle to distinguish semantically similar structures such as doors and walls. To overcome this limitation, this work proposes the first integration of an independent door channel into a predictive model, introducing semantic door cues to optimize predictive occupancy mapping. A dual-channel neural network is constructed based on the CogniPlan dataset and evaluated using a multidimensional assessment framework comprising L1 loss, F1 score, and IoU metrics. The proposed approach effectively enhances map completion in ambiguous regions and significantly improves local geometric inference accuracy. Experimental results demonstrate that the L1 error in door regions is reduced to 0.000025, with both F1 score and IoU reaching 1.0, substantially outperforming baseline models.
📝 Abstract
Predictive mapping can support robotic exploration and navigation by estimating unseen geometric layouts from partial occupancy observations. However, occupancy-only representations may fail to distinguish semantically different structures with similar geometry. This is particularly relevant for indoor doors, which may appear as occupied cells like walls but indicate possible connected rooms or corridors beyond the observed region. This work investigates whether semantic door cues improve predictive geometric occupancy mapping around such ambiguous regions. We modify a subset of the CogniPlan dataset by inserting door-induced ambiguities into partial occupancy maps while keeping the ground-truth layouts unchanged. We compare a geometry-only control model with a semantic-cued model trained on the same modified dataset, where the semantic-cued model receives an additional door channel. Evaluation uses L1 error, F1 score, and Intersection over Union (IoU) over both the full map and a 10-pixel door-region mask. Full-map performance remains broadly similar between models, but localized door-region results show a clear qualitative improvement: L1 decreases from 0.004342 to 0.000025, while F1 and IoU improve from 0.031311 and 0.015905 to 1.000000 and 1.000000, respectively. These results suggest that semantic cues can improve predictive occupancy completion in regions where geometric observations alone are ambiguous.