Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Highway Discretionary Lane-change Decision and Control Using Model Predictive Control

Zishun Zheng, Yihan Wang, Yuan Lin

TL;DR

This work tackles discretionary highway lane-change under unpredictable traffic by proposing a two-stage framework that combines Nonlinear Model Predictive Control (NMPC) for lane decision with a dynamic bicycle model for control, while leveraging CS-LSTM-based trajectory prediction to forecast surrounding vehicles. The approach balances speed, safety, and lane-change benefits through a multi-objective cost and a threshold-based decision rule, and uses a CS-LSTM predictor on a 49×3 social grid to deliver accurate multi-vehicle forecasts over a horizon of 50 frames. Validation in SUMO shows improved average velocity and safer following distances when using CS-LSTM versus Frozen Time, indicating practical benefits for real-time highway automation. The work suggests further validation with higher-fidelity simulators like CARLA and vehicle-in-the-loop experiments to assess real-world applicability.

Abstract

To enable autonomous vehicles to perform discretionary lane change amidst the random traffic flow on highways, this paper introduces a decision-making and control method for vehicle lane change based on Model Predictive Control (MPC). This approach divides the driving control of vehicles on highways into two parts: lane-change decision and lane-change control, both of which are solved using the MPC method. In the lanechange decision module, the minimum driving costs for each lane are computed and compared by solving the MPC problem to make lane-change decisions. In the lane-change control module, a dynamic bicycle model is incorporated, and a multi-objective cost function is designed to obtain the optimal control inputs for the lane-change process. Additionally, A long-short term memory (LSTM) model is used to predict the trajectories of surrounding vehicles for both the MPC decision and control modules. The proposed lane-change decision and control method is simulated and validated in a driving simulator under random highway traffic conditions.

Highway Discretionary Lane-change Decision and Control Using Model Predictive Control

TL;DR

This work tackles discretionary highway lane-change under unpredictable traffic by proposing a two-stage framework that combines Nonlinear Model Predictive Control (NMPC) for lane decision with a dynamic bicycle model for control, while leveraging CS-LSTM-based trajectory prediction to forecast surrounding vehicles. The approach balances speed, safety, and lane-change benefits through a multi-objective cost and a threshold-based decision rule, and uses a CS-LSTM predictor on a 49×3 social grid to deliver accurate multi-vehicle forecasts over a horizon of 50 frames. Validation in SUMO shows improved average velocity and safer following distances when using CS-LSTM versus Frozen Time, indicating practical benefits for real-time highway automation. The work suggests further validation with higher-fidelity simulators like CARLA and vehicle-in-the-loop experiments to assess real-world applicability.

Abstract

To enable autonomous vehicles to perform discretionary lane change amidst the random traffic flow on highways, this paper introduces a decision-making and control method for vehicle lane change based on Model Predictive Control (MPC). This approach divides the driving control of vehicles on highways into two parts: lane-change decision and lane-change control, both of which are solved using the MPC method. In the lanechange decision module, the minimum driving costs for each lane are computed and compared by solving the MPC problem to make lane-change decisions. In the lane-change control module, a dynamic bicycle model is incorporated, and a multi-objective cost function is designed to obtain the optimal control inputs for the lane-change process. Additionally, A long-short term memory (LSTM) model is used to predict the trajectories of surrounding vehicles for both the MPC decision and control modules. The proposed lane-change decision and control method is simulated and validated in a driving simulator under random highway traffic conditions.
Paper Structure (16 sections, 20 equations, 7 figures, 3 tables, 1 algorithm)

This paper contains 16 sections, 20 equations, 7 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Lane-change Decision
  3. Modelling
  4. Cost Function
  5. Constraints
  6. Future State Prediction
  7. Optimal Lane Selection
  8. Lane-change Control
  9. Dynamic Bicycle Model
  10. Cost Function
  11. Constraints
  12. Simulation
  13. Platform & Rules
  14. Training CS-LSTM
  15. Result & Analysis
  16. ...and 1 more sections

Figures (7)

  • Figure 1: CS-LSTM Model
  • Figure 2: dynamic bicycle model
  • Figure 3: comparison of vehicle longitudinal position prediction
  • Figure 4: lateral position of ego vehicle
  • Figure 5: velocity of ego vehicle
  • ...and 2 more figures