We present an intention estimator algorithm that can deal with dynamic change of the environment in a man-machine system\r\nand will be able to be utilized for an autarkical human-assisting system. In the algorithm, state transition relation of intentions\r\nis formed using a self-organizing map (SOM) from the measured data of the operation and environmental variables with the\r\nreference intention sequence. The operational intention modes are identified by stochastic computation using a Bayesian particle\r\nfilter with the trained SOM. This method enables to omit the troublesome process to specify types of information which should be\r\nused to build the estimator. Applying the proposed method to the remote operation task, the estimatorââ?¬â?¢s behavior was analyzed,\r\nthe pros and cons of the method were investigated, and ways for the improvement were discussed. As a result, it was confirmed\r\nthat the estimator can identify the intention modes at 44ââ?¬â??94 percent concordance ratios against normal intention modes whose\r\nperiods can be found by about 70 percent of members of human analysts. On the other hand, it was found that human analystsââ?¬â?¢\r\ndiscrimination which was used as canonical data for validation differed depending on difference of intention modes. Specifically,\r\nan investigation of intentions pattern discriminated by eight analysts showed that the estimator could not identify the same modes\r\nthat human analysts could not discriminate. And, in the analysis of themultiple different intentions, it was found that the estimator\r\ncould identify the same type of intention modes to human-discriminated ones as well as 62ââ?¬â??73 percent when the first and second\r\ndominant intention modes were considered.
Loading....