AutoSpatial improves VLM spatial reasoning for social navigation by combining minimal manual supervision with auto-labeled VQA pairs and hierarchical training, showing gains up to 20.5% in action prediction over baselines.
A protocol for validating social navigation policies
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2verdicts
UNVERDICTED 2representative citing papers
Survey organizing VLM-based social robot navigation into reasoning, planning, and bridging components with a proposed roadmap for hybrid deployable systems.
citing papers explorer
-
AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning
AutoSpatial improves VLM spatial reasoning for social navigation by combining minimal manual supervision with auto-labeled VQA pairs and hierarchical training, showing gains up to 20.5% in action prediction over baselines.
-
Vision-Language Models for Deployable Social Robot Navigation: Bridging Semantic Reasoning and Low-Level Control
Survey organizing VLM-based social robot navigation into reasoning, planning, and bridging components with a proposed roadmap for hybrid deployable systems.