Holger Voos
5 papers · Latest:
Learning-Based Hierarchical Scene Graph Matching for Robot Localization Leveraging Prior Maps
This paper introduces a learned hierarchical scene graph matching method for robust robot localization by leveraging prior maps like BIMs.
Rule-based High-Level Coaching for Goal-Conditioned Reinforcement Learning in Search-and-Rescue UAV Missions Under Limited-Simulation Training
A hierarchical framework for SAR UAVs combines rule-based high-level coaching with online goal-conditioned RL, improving safety and sample efficiency.
Robust Graph Matching through Semantic Relationship Generation for SLAM
A semantic-enhanced graph matching method for SLAM uses object-structure relations to boost robustness and efficiency in ambiguous indoor environments.
COMPASS: COmpact Multi-channel Prior-map And Scene Signature for Floor-Plan-Based Visual Localization
COMPASS uses multi-channel radial descriptors from floor plans and fisheye images for robust visual localization by exploiting geometric and semantic priors.
Passage-Aware Structural Mapping for RGB-D Visual SLAM
This paper introduces a passage-aware RGB-D VSLAM system that detects and models doorways and passages for improved indoor robot navigation.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.