VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation.
Naoki YokoyamaSehoon HaDhruv BatraJiuguang WangBernadette BucherPublished in: CoRR (2023)
Keyphrases
- natural language
- semantic representations
- computer vision
- language learning
- context dependent
- vision system
- conceptual graphs
- programming language
- linguistic analysis
- semantically equivalent
- real time
- image processing
- semantic knowledge
- semantic models
- semantic web
- semantic similarity
- navigation systems
- syntactic semantic
- semantic structure
- topological map
- semantic interpretation
- specification language
- semantic search
- semantic relationships
- semantic constraints
- domain specific
- object detection
- data sources
- high level
- website