Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Human-Machine Interaction in Automated Vehicles: Reducing Voluntary Driver Intervention

Xinzhi Zhong, Yang Zhou, Varshini Kamaraj, Zhenhao Zhou, Wissam Kontar, Dan Negrut, John D. Lee, Soyoung Ahn

TL;DR

This work addresses voluntary driver interventions in automated vehicles and their destabilizing effects on traffic. It couples an evidence-accumulation model of driver distrust with a deep reinforcement learning–based car-following controller to reduce interventions and stabilize platoons. The EA framework is calibrated with driving-simulator data via ABC-ASMC, and the control policy is learned with Soft Actor-Critic in a three-vehicle platoon to balance reducing distrust and maintaining string stability. Results show the DRL controller reduces intervention events by approximately 12–30% and dampens disturbances compared with IDM-PID and HL baselines, indicating improved traffic safety and efficiency in human-AV interactions.

Abstract

This paper develops a novel car-following control method to reduce voluntary driver interventions and improve traffic stability in Automated Vehicles (AVs). Through a combination of experimental and empirical analysis, we show how voluntary driver interventions can instigate substantial traffic disturbances that are amplified along the traffic upstream. Motivated by these findings, we present a framework for driver intervention based on evidence accumulation (EA), which describes the evolution of the driver's distrust in automation, ultimately resulting in intervention. Informed through the EA framework, we propose a deep reinforcement learning (DRL)-based car-following control for AVs that is strategically designed to mitigate unnecessary driver intervention and improve traffic stability. Numerical experiments are conducted to demonstrate the effectiveness of the proposed control model.

Human-Machine Interaction in Automated Vehicles: Reducing Voluntary Driver Intervention

TL;DR

This work addresses voluntary driver interventions in automated vehicles and their destabilizing effects on traffic. It couples an evidence-accumulation model of driver distrust with a deep reinforcement learning–based car-following controller to reduce interventions and stabilize platoons. The EA framework is calibrated with driving-simulator data via ABC-ASMC, and the control policy is learned with Soft Actor-Critic in a three-vehicle platoon to balance reducing distrust and maintaining string stability. Results show the DRL controller reduces intervention events by approximately 12–30% and dampens disturbances compared with IDM-PID and HL baselines, indicating improved traffic safety and efficiency in human-AV interactions.

Abstract

This paper develops a novel car-following control method to reduce voluntary driver interventions and improve traffic stability in Automated Vehicles (AVs). Through a combination of experimental and empirical analysis, we show how voluntary driver interventions can instigate substantial traffic disturbances that are amplified along the traffic upstream. Motivated by these findings, we present a framework for driver intervention based on evidence accumulation (EA), which describes the evolution of the driver's distrust in automation, ultimately resulting in intervention. Informed through the EA framework, we propose a deep reinforcement learning (DRL)-based car-following control for AVs that is strategically designed to mitigate unnecessary driver intervention and improve traffic stability. Numerical experiments are conducted to demonstrate the effectiveness of the proposed control model.
Paper Structure (9 sections, 19 equations, 14 figures, 1 table)

This paper contains 9 sections, 19 equations, 14 figures, 1 table.

Table of Contents

  1. Introduction
  2. Driver Intervention and Its Impact on Traffic
  3. Evidence Accumulation Modeling for Driver Intervention
  4. Model Calibration through Driving Simulator Experiment
  5. Effects of Driver Interventions on Vehicle Kinematics and Disturbance Evolution
  6. AV Longitudinal Control to Reduce Impacts of the Interventions
  7. Control Performance
  8. Conclusions
  9. Acknowledgements

Figures (14)

  • Figure 1: Driving Simulator Experiment
  • Figure 2: Experimental Setting in the Driving Simulator
  • Figure 3: EA models calibrated by ABC-ASMC (a) Marginal Distribution (b) Correlation Matrix
  • Figure 4: Evidence Accumulation in the Driving Simulator (a) Cumulative Distribution of Takeover Time-point (b) Evidence Accumulation for Intervention Events
  • Figure 5: Impact of Driver Intervention on Vehicle Kinematics from Driving Simulator (a) Typical Example in Aggressive Automation Setting (b) Typical Example in Conservative Automation setting (c) Example of Driver Takeover During Acceleration Phase
  • ...and 9 more figures