Human-Machine Adaptive Shared Control for Safe Automated Driving under Automation Degradation

TL;DR

This paper introduces an adaptive shared control system for automated vehicles that dynamically adjusts control authority between human drivers and automation to maintain safety during automation performance degradation.

Contribution

It proposes a novel risk assessment and adaptive control allocation framework that enhances safety by reallocating control authority in response to automation degradation.

Findings

Effective in reducing risk during automation degradation

Improves driver engagement when automation performance drops

Validated through experiments in various driving scenarios

Abstract

In this paper, a human-machine adaptive shared control method is proposed for automated vehicles (AVs) under automation performance degradation. First, a novel risk assessment module is proposed to monitor driving behavior and evaluate automation performance degradation for AVs. Then, an adaptive control authority allocation module is developed. In the event of any performance degradation detection, the allocated control authority of the automation system is decreased based on the assessed risk to reduce the potential risk of vehicle motion. Consequently, the control authority allocated to the human driver is adaptively increased and thus requires more driver engagement in the control loop to compensate for the automation degradation and ensure AV safety. Experimental validation is conducted under different driving scenarios. The testing results show that the proposed approach is able to effectively compensate for the performance degradation of vehicle automation through the human-machine adaptive shared control, ensuring the safety of automated driving