Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Incorporating lane-change prediction into energy-efficient speed control of connected autonomous vehicles at intersections

Maziar Zamanpour, Suiyi He, Michael W. Levin, Zongxuan Sun

TL;DR

This work tackles energy-efficient speed control for connected autonomous vehicles at intersections amid lane-change maneuvers by other drivers. It introduces a lane-change–aware framework that couples a modified Payne–Whitham traffic model with LC prediction and an horizon-based optimal-control solver, using UKF for traffic-state estimation and SPaT information. The approach demonstrates up to 13% average energy savings at substantial CV penetration, while maintaining modest travel-time impact and improving traffic-prediction accuracy, validated in SUMO with mixed platoons and varying market penetration rates. The framework advances practical eco-driving for CAVs by accounting for LC-induced state changes and linking short-term prediction to energy-efficient control in real-world-like, multi-lane intersections.

Abstract

Connected and autonomous vehicles (CAVs) possess the capability of perception and information broadcasting with other CAVs and connected intersections. Additionally, they exhibit computational abilities and can be controlled strategically, offering energy benefits. One potential control strategy is real-time speed control, which adjusts the vehicle speed by taking advantage of broadcasted traffic information, such as signal timings. However, the optimal control is likely to increase the gap in front of the controlled CAV, which induces lane changing by other drivers. This study proposes a modified traffic flow model that aims to predict lane-changing occurrences and assess the impact of lane changes on future traffic states. The primary objective is to improve energy efficiency. The prediction model is based on a cell division platform and is derived considering the additional flow during lane changing. An optimal control strategy is then developed, subject to the predicted trajectory generated for the preceding vehicle. Lane change prediction estimates future speed and gap of vehicles, based on predicted traffic states. The proposed framework outperforms the non-lane change traffic model, resulting in up to 13% energy savings when lane changing is predicted 4-6 seconds in advance.

Incorporating lane-change prediction into energy-efficient speed control of connected autonomous vehicles at intersections

TL;DR

This work tackles energy-efficient speed control for connected autonomous vehicles at intersections amid lane-change maneuvers by other drivers. It introduces a lane-change–aware framework that couples a modified Payne–Whitham traffic model with LC prediction and an horizon-based optimal-control solver, using UKF for traffic-state estimation and SPaT information. The approach demonstrates up to 13% average energy savings at substantial CV penetration, while maintaining modest travel-time impact and improving traffic-prediction accuracy, validated in SUMO with mixed platoons and varying market penetration rates. The framework advances practical eco-driving for CAVs by accounting for LC-induced state changes and linking short-term prediction to energy-efficient control in real-world-like, multi-lane intersections.

Abstract

Connected and autonomous vehicles (CAVs) possess the capability of perception and information broadcasting with other CAVs and connected intersections. Additionally, they exhibit computational abilities and can be controlled strategically, offering energy benefits. One potential control strategy is real-time speed control, which adjusts the vehicle speed by taking advantage of broadcasted traffic information, such as signal timings. However, the optimal control is likely to increase the gap in front of the controlled CAV, which induces lane changing by other drivers. This study proposes a modified traffic flow model that aims to predict lane-changing occurrences and assess the impact of lane changes on future traffic states. The primary objective is to improve energy efficiency. The prediction model is based on a cell division platform and is derived considering the additional flow during lane changing. An optimal control strategy is then developed, subject to the predicted trajectory generated for the preceding vehicle. Lane change prediction estimates future speed and gap of vehicles, based on predicted traffic states. The proposed framework outperforms the non-lane change traffic model, resulting in up to 13% energy savings when lane changing is predicted 4-6 seconds in advance.
Paper Structure (24 sections, 48 equations, 10 figures, 4 tables)

This paper contains 24 sections, 48 equations, 10 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Literature review
  3. Contributions
  4. Framework
  5. Traffic Prediction
  6. Density equation derivation
  7. Speed equation derivation
  8. Modified PW model
  9. Measurement Equations
  10. Lane change model
  11. Optimal control
  12. Vehicle dynamics
  13. Objective function
  14. Constraints
  15. Numerical results
  16. ...and 9 more sections

Figures (10)

  • Figure 1: Problem description: other vehicles perform lane-changing in front of target CAV, which is inconsistent with the predicted driving plan
  • Figure 2: Framework demonstration and process including CAV and SPaT messages, UKF, traffic models, and finally the optimal control
  • Figure 3: Sketch of the incoming and outgoing flows for the target cell. In this case, additional flow will be entered to the target cell from the source lane due to LC in addition to upstream and downstream flows
  • Figure 4: A section of the scenario, modeled traffic stream are loaded on the network, and red vehicle is the target CAV controlled by the optimal strategy
  • Figure 5: Target CAV energy consumptions at 70% MPR for the speed control compared to Krauss car-following model for 20 generated scenarios
  • ...and 5 more figures