視野拡張と空間関係予測で指示に基づく移動を改善
Are We There Yet? Learning to Localize in Embodied Instruction Following
ALFREDベンチマークにおいて、ナビゲーション中の視野を複数角度に拡張し、各時刻で目標地点との相対空間関係を予測させることで、目標位置の特定と移動の精度を向上させた研究。
著者: Shane Storks, Qiaozi Gao, Govind Thattai, Gokhan Tur
分類: cs.AI, cs.CL, cs.CV, cs.RO
原文アブストラクト
Embodied instruction following is a challenging problem requiring an agent to infer a sequence of primitive actions to achieve a goal environment state from complex language and visual inputs. Action Learning From Realistic Environments and Directives (ALFRED) is a recently proposed benchmark for this problem consisting of step-by-step natural language instructions to achieve subgoals which compose to an ultimate high-level goal. Key challenges for this task include localizing target locations and navigating to them through visual inputs, and grounding language instructions to visual appearance of objects. To address these challenges, in this study, we augment the agent's field of view during navigation subgoals with multiple viewing angles, and train the agent to predict its relative spatial relation to the target location at each timestep. We also improve language grounding by introducing a pre-trained object detection module to the model pipeline. Empirical studies show that our approach exceeds the baseline model performance.
