身体性を持つ空間知能:暗黙的シーン表現から空間推論へ
Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning
自然言語指示に基づいて実世界で知覚・行動するロボットの実現に向け、暗黙的ニューラル表現によるシーン表現と、LLMの空間推論能力を高める手法を提案した博士論文。
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: Jiading Fang
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
This thesis introduces "Embodied Spatial Intelligence" to address the challenge of creating robots that can perceive and act in the real world based on natural language instructions. To bridge the gap between Large Language Models (LLMs) and physical embodiment, we present contributions on two fronts: scene representation and spatial reasoning. For perception, we develop robust, scalable, and accurate scene representations using implicit neural models, with contributions in self-supervised camera calibration, high-fidelity depth field generation, and large-scale reconstruction. For spatial reasoning, we enhance the spatial capabilities of LLMs by introducing a novel navigation benchmark, a method for grounding language in 3D, and a state-feedback mechanism to improve long-horizon decision-making. This work lays a foundation for robots that can robustly perceive their surroundings and intelligently act upon complex, language-based commands.
