Augmented Commonsense Knowledge for Remote Object Grounding
This work addresses the challenge of improving agent navigation in photo-realistic unseen environments for vision-and-language navigation tasks, representing an incremental advancement by enhancing existing methods with commonsense knowledge.
The paper tackles the problem of insufficient visual representation for action prediction in vision-and-language navigation, particularly in the REVERIE task with high-level instructions, by proposing an augmented commonsense knowledge model that integrates commonsense information as a spatio-temporal knowledge graph, resulting in state-of-the-art performance on the REVERIE benchmark.
The vision-and-language navigation (VLN) task necessitates an agent to perceive the surroundings, follow natural language instructions, and act in photo-realistic unseen environments. Most of the existing methods employ the entire image or object features to represent navigable viewpoints. However, these representations are insufficient for proper action prediction, especially for the REVERIE task, which uses concise high-level instructions, such as ''Bring me the blue cushion in the master bedroom''. To address enhancing representation, we propose an augmented commonsense knowledge model (ACK) to leverage commonsense information as a spatio-temporal knowledge graph for improving agent navigation. Specifically, the proposed approach involves constructing a knowledge base by retrieving commonsense information from ConceptNet, followed by a refinement module to remove noisy and irrelevant knowledge. We further present ACK which consists of knowledge graph-aware cross-modal and concept aggregation modules to enhance visual representation and visual-textual data alignment by integrating visible objects, commonsense knowledge, and concept history, which includes object and knowledge temporal information. Moreover, we add a new pipeline for the commonsense-based decision-making process which leads to more accurate local action prediction. Experimental results demonstrate our proposed model noticeably outperforms the baseline and archives the state-of-the-art on the REVERIE benchmark.