位置訪問予測によるナビゲーション指示から連続制御動作への変換
Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction
自然言語の指示と生の観測からドローンの連続制御を学習する手法を提案し、訪問位置分布を予測して行動選択に用いることで既存手法より16.85%高いタスク完了精度を実現した。
著者: Valts Blukis, Dipendra Misra, Ross A. Knepper, Yoav Artzi
分類: cs.RO, cs.AI, cs.CL, cs.CV, cs.LG
原文アブストラクト
We propose an approach for mapping natural language instructions and raw observations to continuous control of a quadcopter drone. Our model predicts interpretable position-visitation distributions indicating where the agent should go during execution and where it should stop, and uses the predicted distributions to select the actions to execute. This two-step model decomposition allows for simple and efficient training using a combination of supervised learning and imitation learning. We evaluate our approach with a realistic drone simulator, and demonstrate absolute task-completion accuracy improvements of 16.85% over two state-of-the-art instruction-following methods.
