International Business Machines Corporation

Zhanhong Yan

Michiaki Tatsubori

Satoshi Masuda

A method is provided for driving model calibration. The method clusters a plurality of vehicle trajectories into a plurality of datasets for different driving styles based on a score. The score is calculated for each vehicle trajectory by an objective entropy weight method. The method trains, for each of the plurality of datasets for the different driving styles relative to an existing target driving model, a respective neural network which inputs a respective one of the plurality of datasets and outputs a respective parameter for the existing target driver model to obtain a plurality of trained neural networks. The existing target driver model is for simulating human driving behaviors. The method performs, for each trained neural network, an online adaptation of the existing target driving model based on a respective output of each of the plurality of trained neural networks to obtain a plurality of adapted driver models.

Measuring driving styles and calibrating driving models

A computer-implemented method is provided for redundancy reduction for driving test scenarios. The method includes receiving an original test set of driving scenarios and a driving model which simulates a vehicle behavior under a driving scenario inputted to the driving model. The method includes, for each driving scenario of the original test set, obtaining vehicle dynamics timeseries data as an output of the driving model. The method includes determining similar driving scenarios by comparing driving model outputs. The method additionally includes creating a new test set of driving scenarios by discarding duplicated ones of the similar driving scenarios from the original test set.

Growing community of inventors

Setagaya-ku, Japan

Zhanhong Yan