Understanding Contexts Inside Robot and Human Manipulation Tasks through Vision-Language Model and Ontology System in Video Streams.
Chen JiangMasood DehghanMartin JägersandPublished in: IROS (2020)
Keyphrases
- language model
- manipulation tasks
- video streams
- human robot interaction
- service robots
- robot navigation
- language modeling
- human activities
- n gram
- robotic systems
- humanoid robot
- video data
- vision system
- probabilistic model
- motion planning
- speech recognition
- information retrieval
- real robot
- mobile robot
- smoothing methods
- video frames
- end effector
- computer vision
- query expansion
- gesture recognition
- mixture model
- real time
- activity recognition
- object detection
- visual servoing
- robotic arm