Autonomous Driving Handover Time Prediction Using Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving systems lack the ability to accurately predict the time available for autonomous driving, leading to potential safety issues when drivers are not adequately prepared to take manual control, as they may be occupied or caught off guard during transitions from autonomous to manual driving.
Innovation Solution
An apparatus and method that utilize remote sensors, vehicle dynamics sensors, positioning arrangements, route planning, and real-time information acquisition to calculate and display the time available for autonomous driving, incorporating factors like road infrastructure, traffic, and weather conditions, ensuring the driver is prepared for a smooth transition to manual control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the driver is allowed to perform activities during autonomous driving mode, then the driver's readiness to respond to manual control requests is reduced, but the driver can utilize the autonomous driving time for other activities
Solution Approach 1:
The system performs preliminary actions by calculating and notifying the driver in advance about the upcoming handover time and location. The processor determines when manual control will be needed and provides notification to the driver before the handover occurs, allowing the driver to prepare mentally and physically for transitioning from autonomous to manual control mode.
2Loss of time
If the system provides notification to the driver about handover requirements, then the driver is alerted in time, but the notification may catch an occupied driver off guard and affect their readiness to respond
Solution Approach 1:
The system implements feedback by continuously monitoring driver state and providing notifications about upcoming handovers. The processor determines the handover time based on route information and sensor data, then provides feedback to the driver through appropriate interfaces, creating a closed-loop communication that keeps the driver informed about system status and upcoming transitions.
3Measurement precision
If the system calculates handover time based on route and sensor data, then accurate prediction of autonomous driving time is achieved, but the system complexity increases
Solution Approach 1:
The system achieves multi-functionality by using a single processor to perform multiple tasks: acquiring sensor data from various sources, determining vehicle dynamics parameters, calculating handover time based on route information, and controlling notifications to the driver. This consolidates multiple functions into one component, reducing overall system complexity while maintaining prediction accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided are a method and an apparatus (1) for prediction of time available for autonomous driving, in a vehicle (2) having autonomous driving capabilities and comprising remote sensors (3) arranged to acquire vehicle surrounding information (4) and vehicle dynamics sensors (5) arranged to determine vehicle dynamics parameters (6), as well as a vehicle (2) comprising such an apparatus (1). At least one of a positioning arrangement (7) that provides map data with associated information; a route planning arrangement (8) that enables route planning; and a real time information acquiring arrangement, that acquires at least one of real time traffic information (9a) and real time weather information (9b). The time available is calculated based on a planned route and at least one of vehicle surrounding information (4), vehicle dynamics parameters (6), map data with associated information, real time traffic information (9a) and real time weather information (9b), for the planned route. The calculated time is output to a human machine interface (11) arranged in a vehicle (2).