視覚と言語によるナビゲーションエージェントの行動分析
Behavioral Analysis of Vision-and-Language Navigation Agents
視覚と言語によるナビゲーション(VLN)エージェントが、停止・旋回・移動などの指示をどの程度正しく実行できるかを、スキル別の介入実験で分析した研究。
著者: Zijiao Yang, Arjun Majumdar, Stefan Lee
分類: cs.CV, cs.RO
原文アブストラクト
To be successful, Vision-and-Language Navigation (VLN) agents must be able to ground instructions to actions based on their surroundings. In this work, we develop a methodology to study agent behavior on a skill-specific basis -- examining how well existing agents ground instructions about stopping, turning, and moving towards specified objects or rooms. Our approach is based on generating skill-specific interventions and measuring changes in agent predictions. We present a detailed case study analyzing the behavior of a recent agent and then compare multiple agents in terms of skill-specific competency scores. This analysis suggests that biases from training have lasting effects on agent behavior and that existing models are able to ground simple referring expressions. Our comparisons between models show that skill-specific scores correlate with improvements in overall VLN task performance.
