Automated Lateral Guidance Lane Branch Takeover
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing lateral guidance systems for vehicles are not reliable enough for hands-off mode, as they are susceptible to environmental conditions and errors in lane information recognition, leading to potential vehicle straying from the lane.
Innovation Solution
A method that combines satellite-based position data and high-resolution map data with sensor data from environment sensors to determine the vehicle's position and the most probable lane of occupancy, and uses this information to output a takeover request to the user when a branching lane is detected, ensuring safe operation even with erroneous data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If sensor data from environment sensors is used for lane recognition, then the lateral guidance system can operate with hands-off mode, but the system becomes susceptible to environmental conditions and errors in lane information recognition
Solution Approach 1:
The patent combines multiple data sources including sensor data from environment sensors (cameras, radar), satellite-based position data, and high-resolution map data to determine lane information. This fusion of multiple independent data sources compensates for the weaknesses of individual sensors under environmental conditions while maintaining hands-off automation capability.
Solution Approach 2:
The system continuously monitors the determined lane information and compares it with expected lane profiles from map data and satellite positioning. When deviations or uncertainties are detected, the system can request user confirmation or switch to hands-on mode, providing feedback-based reliability enhancement.
2Reliability
If the system requests user takeover at every branching lane, then safety is improved, but the user experience deteriorates due to excessive takeover requests
Solution Approach 1:
Instead of requesting takeover at all branching lanes, the system selectively requests user intervention only when the determined lane with highest probability of occupancy is adjacent to a branching lane. This partial action approach maintains safety where needed while avoiding unnecessary takeover requests in clear situations.
Solution Approach 2:
The system uses probability thresholds and spatial parameters to dynamically determine when takeover requests are necessary. By changing the decision parameters based on the specific situation (lane occupancy probability, distance to branch, confidence level), the system optimizes the balance between safety and user experience.
Data Source
AI summary
A method for assisting a user of a vehicle during an automated lateral guidance of the vehicle on a road having multiple lanes includes determining map-based position data describing a current position of the vehicle in relation to the lanes on the basis of satellite-based position data and high-resolution map data, receiving sensor data from at least one environment sensor of the vehicle describing boundaries of the lanes, detecting a branch of the road on the basis of the map-based position data and/or the sensor data, wherein at least one of the lanes branches off from the remaining lanes at the branch, and actuating an output device for outputting a takeover request to the user as a function of a position of the lane with the highest stay probability relative to the at least one branching lane.