ADAPT: Vision-Language Navigation with Modality-Aligned Action Prompts.
Bingqian LinYi ZhuZicong ChenXiwen LiangJianzhuang LiuXiaodan LiangPublished in: CVPR (2022)
Keyphrases
- multi modal
- real time
- action language
- programming language
- vision system
- medical images
- natural language
- language learning
- indoor environments
- image processing
- computer vision
- mobile robot
- human actions
- action selection
- operational semantics
- navigation systems
- logic programs
- changing environment
- computational linguistics
- specification language
- autonomous vehicles
- service robots
- neural network