Jerk-Minimized CILQR for Human-Like Driving on Two-Lane Roadway - Robotics Institute Carnegie Mellon University

Jerk-Minimized CILQR for Human-Like Driving on Two-Lane Roadway

Omid Jahanmahin, Qin Lin, Yanjun Pan, and John M. Dolan
Conference Paper, Proceedings of IEEE Intelligent Vehicles Symposium (IVS '21), pp. 1282 - 1289, July, 2021

Abstract

This work proposes a novel framework for motion planning using trajectory optimization for autonomous driving. First, a two-phase behavioral policy maker (BPM) is proposed as a high-level decision maker to mimic human-like driving style by avoiding unnecessary tasks and early lane changes. Second, a comprehensive study on iterative adaptive weight tuning functions has been done to limit manual weight tuning in the Constrained Iterative Linear Quadratic Regulator (CILQR) motion planner. Third, a jerk-minimized CILQR is presented to ensure the comfort and safety of passengers by generating smooth trajectories. The simulation results show efficiency, safety, and comfort of generated trajectories.

BibTeX

@conference{Jahanmahin-2021-133745,
author = {Omid Jahanmahin and Qin Lin and Yanjun Pan and John M. Dolan},
title = {Jerk-Minimized CILQR for Human-Like Driving on Two-Lane Roadway},
booktitle = {Proceedings of IEEE Intelligent Vehicles Symposium (IVS '21)},
year = {2021},
month = {July},
pages = {1282 - 1289},
keywords = {autonomous driving, motion planning, jerk-minimized trajectory optimization, constrained iLQR, adaptive weight tuning},
}