Understanding Contexts Inside Robot and Human Manipulation Tasks through a Vision-Language Model and Ontology System in a Video Stream.
Chen JiangMasood DehghanMartin JägersandPublished in: CoRR (2020)
Keyphrases
- manipulation tasks
- language model
- video streams
- human robot interaction
- service robots
- robot navigation
- language modeling
- n gram
- human activities
- robotic systems
- probabilistic model
- speech recognition
- video data
- humanoid robot
- vision system
- computer vision
- mixture model
- motion planning
- information retrieval
- test collection
- end effector
- video frames
- autonomous robots
- robotic arm
- degrees of freedom
- gesture recognition
- real time
- mobile robot
- three dimensional
- semantic information
- real robot
- bayesian networks