GPT-4V(ision) for Robotics: Multimodal Task Planning from Human Demonstration.
Naoki WakeAtsushi KanehiraKazuhiro SasabuchiJun TakamatsuKatsushi IkeuchiPublished in: CoRR (2023)
Keyphrases
- robot programming
- human robot interaction
- artificial intelligence
- multi modal
- human centered
- computer vision
- human subjects
- multimedia
- decision support
- planning problems
- ai planning
- multimodal interaction
- creative problem solving
- data sets
- pointing gestures
- multimodal information
- human operators
- human behavior
- domain independent