AutoSpatial: 効率的な空間推論学習による社会的ロボットナビゲーションのための視覚言語推論
AutoSpatial: Visual-Language Reasoning for Social Robot Navigation through Efficient Spatial Reasoning Learning
大規模視覚言語モデルの空間理解を、自動ラベリングしたVQAデータと2段階の階層的学習で強化し、社会的ロボットナビゲーションの知覚・予測・推論・行動・説明を改善する手法を提案。
著者: Yangzhe Kong, Daeun Song, Jing Liang, Dinesh Manocha, Ziyu Yao, Xuesu Xiao
分類: cs.RO
原文アブストラクト
We present a novel method, AutoSpatial, an efficient approach with structured spatial grounding to enhance VLMs' spatial reasoning. By combining minimal manual supervision with large-scale Visual Question-Answering (VQA) pairs auto-labeling, our approach tackles the challenge of VLMs' limited spatial understanding in social navigation tasks. By applying a hierarchical two-round VQA strategy during training, AutoSpatial achieves both global and detailed understanding of scenarios, demonstrating more accurate spatial perception, movement prediction, Chain of Thought (CoT) reasoning, final action, and explanation compared to other SOTA approaches. These five components are essential for comprehensive social navigation reasoning. Our approach was evaluated using both expert systems (GPT-4o, Gemini 2.0 Flash, and Claude 3.5 Sonnet) that provided cross-validation scores and human evaluators who assigned relative rankings to compare model performances across four key aspects. Augmented by the enhanced spatial reasoning capabilities, AutoSpatial demonstrates substantial improvements by averaged cross-validation score from expert systems in: perception & prediction (up to 10.71%), reasoning (up to 16.26%), action (up to 20.50%), and explanation (up to 18.73%) compared to baseline models trained only on manually annotated data.
