Automated Driving HMI for Low-Confidence Decision Assistance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current driver assistance systems in partially and conditionally automated vehicles often require unnecessary handovers of driving control to human drivers due to low confidence levels in making driving decisions, leading to frequent disengagement of automated driving modes and a suboptimal driving experience.
Innovation Solution
An automated driving system that includes a perception module, an intervention module, and a vehicle control module, which detects situations requiring driver assistance, provides options or requests information from the driver through a human-machine interface, and autonomously drives based on driver input or default conservative options if no input is received within a set time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the automated driving system requires driver intervention for low confidence situations, then the reliability of driving decisions is improved, but the extent of automation deteriorates due to frequent handovers
Solution Approach 1:
The system implements feedback by detecting driver states (attention level, workload, stress) and adjusting the confidence threshold dynamically. When driver attention is high, the system lowers the threshold for autonomous operation, allowing more situations to be handled autonomously. When driver attention is low, the threshold increases, requiring more situations to be handled autonomously to maintain safety.
Solution Approach 2:
The system dynamically adapts the confidence threshold based on real-time driver state assessment. The threshold is not fixed but varies according to driver attention, workload, and stress levels, enabling the system to optimize the balance between automation extent and decision reliability adaptively.
2Reliability
If the system requests driver assistance frequently, then the reliability of driving decisions is improved, but the ease of operation deteriorates due to increased driver-system interaction
Solution Approach 1:
The system changes the parameter of confidence threshold dynamically based on driver state. By adjusting this parameter according to driver attention and workload, the system reduces unnecessary requests for driver assistance while maintaining reliable decision-making, thereby improving ease of operation without sacrificing reliability.
3Extent of automation
If the automated driving system maintains autonomous control for longer periods, then the extent of automation is improved, but the reliability deteriorates due to low confidence in making driving decisions
Solution Approach 1:
The system uses feedback from driver state monitoring to adjust autonomous operation thresholds. When drivers are attentive and capable, the system maintains higher extent of automation. When driver state deteriorates, the system reduces automation extent to maintain reliability, creating a dynamic balance between these two parameters.
Data Source
AI summary
An automated driving system includes perception, intervention, and vehicle control modules. The perception module detects an upcoming situation to be experienced by a vehicle. The intervention module: determines that a low confidence level exists for a driving decision to be made for the upcoming situation; enables intervention of an autonomous driving mode and indicate information pertaining to the upcoming situation to a driver of the vehicle via an interface; based on the upcoming situation, requests assistance from the driver by (i) indicating available options for the situation via the interface, or (ii) requesting information from the driver to aid in making the driving decision; and determine whether an input has been received from the driver via the interface indicating (i) a selected one of the available options, or (ii) the requested information. The vehicle control module autonomously drives the vehicle based on whether the input has been received.