SASRA: 連続環境における視覚言語ナビゲーションのための意味論的時空間推論エージェント
SASRA: Semantically-aware Spatio-temporal Reasoning Agent for Vision-and-Language Navigation in Continuous Environments
意味マップと言語をクロスモーダルに接地するTransformer-再帰ハイブリッドモデルで、未知環境での連続3D視覚言語ナビゲーションの汎化性能をSPLで22%以上改善した。
著者: Muhammad Zubair Irshad, Niluthpol Chowdhury Mithun, Zachary Seymour, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar
分類: cs.RO, cs.CL, cs.CV
原文アブストラクト
This paper presents a novel approach for the Vision-and-Language Navigation (VLN) task in continuous 3D environments, which requires an autonomous agent to follow natural language instructions in unseen environments. Existing end-to-end learning-based VLN methods struggle at this task as they focus mostly on utilizing raw visual observations and lack the semantic spatio-temporal reasoning capabilities which is crucial in generalizing to new environments. In this regard, we present a hybrid transformer-recurrence model which focuses on combining classical semantic mapping techniques with a learning-based method. Our method creates a temporal semantic memory by building a top-down local ego-centric semantic map and performs cross-modal grounding to align map and language modalities to enable effective learning of VLN policy. Empirical results in a photo-realistic long-horizon simulation environment show that the proposed approach outperforms a variety of state-of-the-art methods and baselines with over 22% relative improvement in SPL in prior unseen environments.
