Hands-Off Driving Fallback Using Lane Models and Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated driving systems in vehicles are limited to specific driving situations, such as highways with structurally separated directions of travel, restricting the activation of hands-off driving functions to speeds below 60 km/h due to reliance on physical guide rails.
Innovation Solution
A method utilizing a combination of camera-based lane modeling and complementary sensor data, including chassis vibrations and interior acoustics, to create a digital fallback system that enables hands-off driving on highways without structural lane separation by safeguarding lane models and trajectories using multi-sensor fusion and machine learning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the automated driving function relies on physical guide rails for lane separation, then the system has high reliability in detecting lane boundaries, but the adaptability to different driving situations is restricted
Solution Approach 1:
The patent replaces the mechanical/physical guide rail system with an optical sensing system using cameras and image processing. The camera-based lane detection system processes visual information to identify lane boundaries and vehicle position, eliminating dependence on physical guide rails while maintaining detection reliability through advanced image analysis algorithms
Solution Approach 2:
The patent creates a universal lane detection system that functions across multiple driving situations - both highways with guide rails and highways with median strips. The camera-based system adapts to different road configurations by processing various visual patterns, making the automated driving function applicable to diverse driving environments without requiring physical guide rails
2Reliability
If the hands-off driving function is limited to highways with structurally separated directions of travel, then the safety of automated driving is ensured, but the operational range of the system is restricted
Solution Approach 1:
The patent substitutes the mechanical physical barrier (guide rail) with an optical detection system (camera). This replacement allows the system to detect lane boundaries and road edges through visual processing, enabling safe automated operation on highways with median strips where no physical guide rail exists, thereby expanding operational range while maintaining safety through reliable image-based detection
3Device complexity
If physical guide rails are used for lane separation, then the device complexity is low, but the ease of operation in diverse driving conditions is reduced
Solution Approach 1:
The patent replaces the simple mechanical guide rail structure with a camera-based optical detection system. Although the sensing system becomes more complex, it dramatically improves ease of operation by enabling automated driving on various highway configurations including those with median strips, eliminating the restriction to only guide rail-equipped highways
Data Source
AI summary
A method for operating a hands-off driving function of an automated motor vehicle is provided. The method includes determining a first lane model based on image data of a camera which is installed on the automated motor vehicle and the field of view of which covers at least part of the surroundings of the automated motor vehicle, determining a trajectory of the automated motor vehicle based on the first lane model, and driving in an automated manner along the determined trajectory. The method also includes securing the automated driving, the lane model and/or the determined trajectory based on additional sensor data.