Learning RL policies for anticipative assistive robots by simulating human-robot interactions in real scenarios using egocentric videos.
Silvia Abal-FernándezCésar Caramazana-ZarzosaMaría Beatriz Loureiro-CasalderreySantiago MartínezCarlos BalaguerFernando Díaz-de-MaríaIván González-DíazPublished in: ROBIO (2023)
Keyphrases
- human robot
- action selection
- learning process
- reinforcement learning
- learning algorithm
- autonomous robots
- humanoid robot
- robot behavior
- machine learning
- optimal policy
- mobile robot
- domain independent
- markov decision processes
- activity recognition
- human activities
- domain specific
- cooperative
- video sequences
- autonomous learning
- imitation learning
- artificial intelligence