InSpire: 内在的空間推論を備えた視覚-言語-行動モデル
InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning
VLAモデルに「物体はロボットから見てどの方向か」という空間推論を組み込むことで、タスク無関係な視覚特徴への誤相関を抑え、汎化性能を高める手法を提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Ji Zhang, Shihan Wu, Xu Luo, Hao Wu, Lianli Gao, Heng Tao Shen, Jingkuan Song
分類: cs.RO
原文アブストラクト
Leveraging pretrained Vision-Language Models (VLMs) to map language instruction and visual observations to raw low-level actions, Vision-Language-Action models (VLAs) hold great promise for achieving general-purpose robotic systems. Despite their advancements, existing VLAs tend to spuriously correlate task-irrelevant visual features with actions, limiting their generalization capacity beyond the training data. To tackle this challenge, we propose Intrinsic Spatial Reasoning (InSpire), a simple yet effective approach that mitigates the adverse effects of spurious correlations by boosting the spatial reasoning ability of VLAs. Specifically, InSpire redirects the VLA's attention to task-relevant factors by prepending the question "In which direction is the [object] relative to the robot?" to the language instruction and aligning the answer "right/left/up/down/front/back/grasped" and predicted actions with ground-truth. Notably, InSpire can be used as a plugin to enhance existing autoregressive VLAs, requiring no extra training data or interaction with other large models. Extensive experimental results in both simulation and real-world environments demonstrate the effectiveness and flexibility of our approach.
