Robots were used at the site of the World Trade Center disaster, and they are being used to explore the interior of the Fukushima Daiichi Nuclear Plant (FDNP). Robots will be used at the FDNP for the next few decades, until the nuclear reactor is finally decommissioned. Wired communications systems have been used to teleoperate robots in hazardous areas where humans cannot work. In this paper, we show the fluctuation of Wi-Fi power strength in a real environment and that the fluctuations utilization is one of the key points to be considered while developing rescue robots for disaster-prone areas. We propose a simulation environment that simulates the fluctuation of the Wi-Fi power strength with a database and evaluates the performance of the robot with unstable Wi-Fi connectivity.
We propose an automated method for predicting subject behaviors based on first-person vision in an area surrounding bookshelves. The proposal classifies each frame within a movie recorded using a head-mounted camera to the six primitive behaviors according to naive Bayes nearest-neighbor method (NBNN). A prediction experiment is conducted using two image sequences recorded by a head-mounted camera. The experimental results confirm that the average classification rates for NBNN with random sampling (including principal components analysis) are improved from 0.09 to 0.13 for one data set and from 0.03 to 0.08 for the other data set compared with the bag-of-features and support vector machine combination results.