데이터기반 운동감 생성법 및 차량 시뮬레이터 통합

To improve the reality of motion simulator, a data-driven motion generation method has been introduced that simply records and replays the motion of real vehicles. We can achieve high quality of reality from real samples, but it has no interactions between users and simulations. However, in character animation, user controllable motions are generated by the motion capture database and appropriate control algorithms. In this study, as a tool for the interactive data-driven driving simulator, we proposed a new motion generation method. We sampled the motion data from a real vehicle, transformed the data into the appropriate data structure(motion block), and saved the series of it into a database. During simulation, our system searched and synthesized optimal motion blocks and provided a motion stream reflecting current simulation conditions and parameterized user demands. We demonstrate the value of the proposed method through experiments with the integrated motion base system.