Multimodal Aggregation Approach for Memory Vision-Voice Indoor Navigation with Meta-Learning

1 Sep 2020  ·  Liqi Yan, Dongfang Liu, Yaoxian Song, Changbin Yu ·

Vision and voice are two vital keys for agents' interaction and learning. In this paper, we present a novel indoor navigation model called Memory Vision-Voice Indoor Navigation (MVV-IN), which receives voice commands and analyzes multimodal information of visual observation in order to enhance robots' environment understanding. We make use of single RGB images taken by a first-view monocular camera. We also apply a self-attention mechanism to keep the agent focusing on key areas. Memory is important for the agent to avoid repeating certain tasks unnecessarily and in order for it to adapt adequately to new scenes, therefore, we make use of meta-learning. We have experimented with various functional features extracted from visual observation. Comparative experiments prove that our methods outperform state-of-the-art baselines.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Visual Navigation AI2-THOR MVV-IN SPL (All) 17.27 # 1
Success Rate (All) 48.7 # 1
SPL (L≥5) 13.63 # 2
Success Rate (L≥5) 30.9 # 1

Methods


No methods listed for this paper. Add relevant methods here