Text-driven object affordance for guiding grasp-type recognition in multimodal robot teaching.
Naoki WakeDaichi SaitoKazuhiro SasabuchiHideki KoikeKatsushi IkeuchiPublished in: Mach. Vis. Appl. (2023)
Keyphrases
- physical objects
- document analysis
- mobile robot
- recognition rate
- partially occluded objects
- object recognition
- object models
- position and orientation
- d objects
- object description
- object classes
- partial occlusion
- e learning
- three dimensional objects
- information retrieval
- complex objects
- vision system
- learning companion
- object model
- object representation
- path planning
- learning process
- robotic systems
- computer programming
- learning environment
- multi robot
- recognition algorithm
- text mining
- occluded objects
- distance learning
- multi modal
- feature extraction
- image retrieval
- multiple modalities
- multimedia
- objects in cluttered scenes
- individual objects
- configuration space
- keywords
- autonomous robots
- spatial relations
- action recognition
- online learning