A state representation unaffected by environmental changes

To interact with the external environment, robots represent it as a state using sensor data. In this study, we present a state representation based on noisy sensor data using distances among probability distributions. The representation is robust to environmental changes, in other words, the robot can recognize its sensor signals with a certain environmental changes as an identical state. We represent sensor signals as probability distributions; the distances between such distributions express a state. To confirm the effectiveness of our proposed state representation, we conducted experiments using a mobile robot with distance sensors. Experimental results confirmed that our proposed representation correctly recognizes similar states using a converted sensor signal.