analiza aiqbench
CrossMaps advances autonomous rover navigation by integrating confidence-aware fusion of CLIP embeddings with a dual-memory architecture to handle noisy sensor data in real time. This approach enables the construction of language-queryable semantic maps that persist critical landmarks while filtering out unreliable observations, directly addressing partial observability challenges in robotics. The system is designed for deployment on Jetson Orin hardware alongside SLAM pipelines, bridging high-level AI perception with low-level navigation control.
CrossMaps: Confidence-Aware Open-Vocabulary Semantic Mapping for Rover Navigation
arXiv:2606.16935v1 Announce Type: cross Abstract: Rovers rely on perception to maintain spatial maps that encode both objects and sensor quality (e.g., range reliability, lighting artifacts, data density), guiding data fusion, embedding updates, and navigation under partial observability. To study these coupled perception-navigation processes, we present CrossMaps, a real-time confidence-aware open-vocabulary semantic mapping pipeline that constructs language-queryable maps from RGB-D data. Building on VLMaps-style approaches, CrossMaps integrates multi-scale CLIP embeddings with confidence-aware fusion and a dual-memory architecture consisting of Short-Term Memory (STM) and Long-Term Memory (LTM). The STM aggregates noisy visual observations using geometric, semantic, and temporal confidence cues, while confident and coherent cells are promoted to the LTM as persistent semantic landmarks. Designed for deployment with a Jetson Orin-powered UGV alongside SLAM, CrossMaps runs in real time and produces semantic heatmaps that can be queried with natural language to guide rover navigation.
Abstract:Rovers rely on perception to maintain spatial maps that encode both objects and sensor quality (e.g., range reliability, lighting artifacts, data density), guiding data fusion, embedding updates, and navigation under partial observability. To study these coupled perception-navigation processes, we present CrossMaps, a real-time confidence-aware open-vocabulary semantic mapping pipeline that constructs language-queryable maps from RGB-D data. Building on VLMaps-style approaches, CrossMaps integrates multi-scale CLIP embeddings with confidence-aware fusion and a dual-memory architecture consisting of Short-Term Memory (STM) and Long-Term Memory (LTM). The STM aggregates noisy visual observations using geometric, semantic, and temporal confidence cues, while confident and coherent cells are promoted to the LTM as persistent semantic landmarks. Designed for deployment with a Jetson Orin-powered UGV alongside SLAM, CrossMaps runs in real time and produces semantic heatmaps that can be queried with natural language to guide rover navigation.
Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2606.16935 [cs.RO]
(or arXiv:2606.16935v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.16935 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 160 cuvinte
Subiecte conexe
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
LessWrong · 8 oct. 2026
OpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot Perception
arXiv · 7 oct. 2026
Vision-Language-Motion Maps: An Open-Vocabulary, Uncertainty-Aware, Queryable Motion Attribute for 3D Scene Maps
arXiv · 20 iul. 2026
SuperMap: A Spatio-Temporal SLAM System for Visual-Language Navigation
arXiv · 25 aug. 2026