Novel Pure-Pursuit Trajectory Following Approaches and their Practical Applications

Abstract

Pure-pursuit algorithm is a popular trajectory tracking algorithm, widely used in mobile robotics and vehicular control for numerous reasons. The operation is simple and straightforward as it depends only on the kinematic model of the target mechanical system. The algorithm can be tuned by choosing look-ahead distance of points of the reference trajectory. On the other hand, pure-pursuit suffers from weaknesses highly attributed to improper selection of look-ahead distance, resulting in poor tracking performance. Recent developments focused on overcoming this drawback by dynamical change of this parameter. In this paper, we propose three enhancements to the original pure-pursuit algorithm, aiming to handle dynamic selection of look-ahead distance by selecting multiple goals, modifying look-ahead distance according to the curvatures and adjusting lateral deviation. Our work was motivated by an ongoing autonomous vehicle research at our university.