Inferring Human-Robot Performance Objectives During Locomotion Using Inverse Reinforcement Learning and Inverse Optimal Control.
Wentao LiuJunmin ZhongRuofan WuBretta L. FylstraJennie SiHe Helen HuangPublished in: IEEE Robotics Autom. Lett. (2022)
Keyphrases
- optimal control
- human robot
- inverse reinforcement learning
- robotic systems
- human robot interaction
- reinforcement learning
- action selection
- temporal difference
- preference elicitation
- reward function
- dynamic programming
- control strategy
- dialogue system
- mobile robot
- humanoid robot
- infinite horizon
- artificial life
- partially observable
- vision system
- mathematical model
- evaluation function
- artificial intelligence
- evolutionary algorithm
- average cost
- human users
- markov chain
- domain independent