AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments.
Sudipta PaulAmit Roy-ChowdhuryAnoop CherianPublished in: NeurIPS (2022)
Keyphrases
- physical world
- dynamic environments
- multimedia
- visual information
- signal processing
- real world
- audio visual
- music score
- situated agents
- audio signals
- obstacle avoidance
- service robots
- highly dynamic
- multimedia information
- intelligent agents
- web navigation
- shopping malls
- visual data
- real time
- multi modal
- mobile robot
- user interface
- feature vectors
- metadata
- artificial intelligence
- learning algorithm
- neural network