Icon Legend

This session is not in your schedule.

This session is in your schedule. Click again to remove it.

97 Views

Abstract for presentation (Poster or Podium)

Intelligent Transportation Systems

Online Learning-based Model Predictive Trajectory Control for CAVs: Modeling and Physical Tests

Monday, June 17, 2024

1:30 PM - 2:45 PM ET

Room: Galleria

Primary Author(s)

QL

Qianwen Li

Assistant Professor
University of Georgia
Athens, GA, United States

Co-Author(s)

PZ

Peng Zhang, n/a

PhD Student
University of Wisconsin – Madison
madison, Wisconsin, United States
HY

Handong Yao (he/him/his)

Assistant Professor
University of Georgia
Athens, GA, United States
Zhiwei Chen, Ph.D.

Assistant Professor
Drexel University, United States
Xiaopeng Li, PhD

Professor
University of Wisconsin–Madison, United States

Submitter(s)

CL

Cami Li

University of Georgia
athens, Georgia, United States

Abstract: Motivated by the promising benefits of connected and autonomous vehicles (CAVs) in improving fuel efficiency, mitigating congestion, and enhancing safety, numerous theoretical models have been proposed to plan CAV multiple-step trajectories (time-specific speed and location trajectories) to accomplish various operations. However, limited efforts have been made to develop proper trajectory control techniques to regulate vehicle movements to follow multiple-step trajectories and test the performance of theoretical trajectory planning models with field experiments. Without an effective control method, the benefits of theoretical models for CAV trajectory planning can be difficult to harvest. Therefore, this study proposes an online learning-based model predictive vehicle trajectory control structure to follow time-specific speed and location profiles. Unlike single-step controllers that are dominantly used in the literature, a multiple-step model predictive controller is adopted to control the vehicle’s longitudinal movements for higher accuracy. The model predictive controller output (speed) cannot be interpreted by vehicles. A reinforcement learning agent is used to dynamically convert the speed value to the vehicle’s direct control variable (i.e., throttle/brake). The reinforcement learning agent captures real-time changes in the operating environment. This is valuable in saving parameter calibration resources and improving trajectory control accuracy. A line tracking controller keeps vehicles on track by regulating the lateral motions. The proposed control structure is tested using reduced-scale robot cars. The adaptivity of the proposed control structure is demonstrated by changing the vehicle load. Then, experiments on two fundamental CAV platoon operations (i.e., platooning and split) show the effectiveness of the proposed trajectory control structure in regulating robot movements to follow time-specific reference trajectories against a benchmark.

Learning Objectives:

Attendees can expect to learn the following from this session:

Upon completion, participant will be able to understand an online learning-based model predictive vehicle trajectory control structure.
Upon completion, participant will be able to grasp how to use reinforcement learning to enable the control structure adaptivity.
Upon completion, participant will be able to understand the significance of accurate vehicle control.