Use of Large Sample Sizes and Multiple Evaluation Methods in Human-Robot Interaction Experimentation.
Cindy L. BethelRobin R. MurphyPublished in: AAAI Spring Symposium: Experimental Design for Real-World Systems (2009)
Keyphrases
- evaluation methods
- human robot interaction
- sample size
- evaluation method
- human robot
- evaluation metrics
- model selection
- statistical power
- evaluation criteria
- upper bound
- robot programming
- evaluation methodology
- humanoid robot
- gesture recognition
- confidence intervals
- worst case
- learning algorithm
- random sampling
- service robots