Node Point Optimization for Local Trajectory Planners based on Human Preferences

There is an increased number of Driver Assistance systems on the field, therefore the need of having naturalistic behavior of these functions is increasing. In our work the trajectory planning task is analyzed. A clothoid-based local trajectory planning algorithm is proposed, which relies on node points within the look ahead distance. The node point distances were optimized to yield a global trajectory which is close to the human drivers’ path. Real driving data was used as the optimization reference. As a result of the optimization, we were able to determine a characteristic node point distance set which fits all drivers. We have also shown that three node points within a look ahead distance of 140 m are sufficient to describe the drivers’ trajectory. Later this result will serve as a basis to build a driver model which calculates the lateral coordinates of the node points.