Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Learning in the presence of concept drift and hidden contexts
Machine Learning
Maintaining Stream Statistics over Sliding Windows
SIAM Journal on Computing
Using Decision Trees for Agent Modeling: Improving Prediction Performance
User Modeling and User-Adapted Interaction
User Modeling for Adaptive News Access
User Modeling and User-Adapted Interaction
PEXIS: Probabilistic experience representation based adaptive interaction system for personal robots
Systems and Computers in Japan
MOSAIC Model for Sensorimotor Learning and Control
Neural Computation
Learning drifting concepts: Example selection vs. example weighting
Intelligent Data Analysis
Detecting change in data streams
VLDB '04 Proceedings of the Thirtieth international conference on Very large data bases - Volume 30
ROBIO '09 Proceedings of the 2008 IEEE International Conference on Robotics and Biomimetics
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Learning and interacting in human-robot domains
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Hi-index | 0.00 |
This article presents a method for tele-operated mobile robots to rapidly adapt to behavior policies. Since real-time adaptation requires frequent observations of sensors and the behavior of users, rapid policy adaptation cannot be achieved when significant data are not differentiated from insignificant data in every process cycle. Our method solves this problem by evaluating the significance of data for learning based on changes in the degree of confidence. A small change in the degree of confidence can be regarded as reflecting insignificant data for learning (that data can be discarded). Accordingly, the system can avoid having to store experience data too frequently, and the robot can adapt more rapidly to changes in the user's policy. In this article, we confirm that by taking advantage of a significance evaluation not only of proposition of behavior, but also of each proposition of each piece of sensor-level data, a robot can rapidly adapt to a user's policy. We discuss the results of two experiments in static and dynamic environments, in both of which the user switched policies between "avoid" and "approach."