日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

ナビゲーションarXiv:1901.03035

補助的な進捗推定による自己監視型ナビゲーションエージェント

Self-Monitoring Navigation Agent via Auxiliary Progress Estimation

シェア:XThreadsFacebookLINEはてブBluesky

視覚と言語の指示を照合するモジュールと進捗監視を組み合わせ、未知環境でのVision-and-Language Navigationを高精度化した研究。未見テストで成功率を8%向上させ最先端を更新した。

著者: Chih-Yao Ma, Jiasen Lu, Zuxuan Wu, Ghassan AlRegib, Zsolt Kira, Richard Socher, Caiming Xiong

分類: cs.AI, cs.CL, cs.CV, cs.RO

原文アブストラクト

The Vision-and-Language Navigation (VLN) task entails an agent following navigational instruction in photo-realistic unknown environments. This challenging task demands that the agent be aware of which instruction was completed, which instruction is needed next, which way to go, and its navigation progress towards the goal. In this paper, we introduce a self-monitoring agent with two complementary components: (1) visual-textual co-grounding module to locate the instruction completed in the past, the instruction required for the next action, and the next moving direction from surrounding images and (2) progress monitor to ensure the grounded instruction correctly reflects the navigation progress. We test our self-monitoring agent on a standard benchmark and analyze our proposed approach through a series of ablation studies that elucidate the contributions of the primary components. Using our proposed method, we set the new state of the art by a significant margin (8% absolute increase in success rate on the unseen test set). Code is available at https://github.com/chihyaoma/selfmonitoring-agent .

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI