 Autonomous driving planning is a challenging problem when the environment is complicated. It is difficult for the planner to find a good trajectory that navigates safely with crowded surrounding vehicles. To solve this complicated problem, a fast algorithm that generates a high quality safe trajectory is necessary. Constrained Iterative Linear Quadratic Regulator (CILQR) is appropriate for this problem and it successfully generates the required trajectory in real time. This algorithm is based on ILQR, which is a popular approach for nonlinear optimization problem, and it resolved the ILQR's problem. However, CILQR has some deficiencies. Firstly, CILQR uses logarithmic barrier function for hard constraints, but this causes a numerical problem especially when the initial nominal trajectory is infeasible. Secondly, the convergence speed can be varied by the quality of initial trajectory and this might causes an unexpected result. To address these problems, we add two new features for CILQR. The first one is using relaxed logarithmic barrier function instead of the standard logarithmic barrier function to prevent numerical issues. The other one is adding an efficient initial trajectory creator to generate a good initial trajectory. Moreover, this initial trajectory helps CILQR to converge to a desired trajectory. These new features extend CILQR's usage to more practical autonomous driving applications. Simulation results show that our algorithm is effective in challenging driving environments. 


Motion Planning for Autonomous Driving With Extended Constrained Iterative Lqr

Division / Sponsors: 
Dynamic Systems & Control (DSCD)

Paper Proceedings: https://asmedigitalcollection.asme.org/DSCC/DSCC2020/volume/84270

DSCC2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.