ARMCHAIR: integrated inverse reinforcement learning and model predictive control for human-robot collaboration.
Angelo Caregnato-NetoLuciano Cavalcante SiebertArkady ZgonnikovMarcos Ricardo Omena de Albuquerque MáximoRubens Junqueira Magalhães AfonsoPublished in: CoRR (2024)
Keyphrases
- human robot
- model predictive control
- inverse reinforcement learning
- human robot interaction
- control system
- predictive control
- dialogue system
- humanoid robot
- reward function
- preference elicitation
- robotic systems
- action selection
- artificial intelligence
- neural network
- state space
- multi modal
- control scheme
- learning algorithm