Autonomous Driving Control Using Learned User Driving Habits
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems employ a unified strategy that cannot accommodate the diverse behavioral driving habits of different users, leading to a lack of personalized driving experiences and user dissatisfaction.
Innovation Solution
A method and apparatus that determine a user's behavioral driving habit by analyzing their manual driving data and map data, allowing for the adaptation of autonomous driving strategies to match individual preferences, including vehicle-following distance, lane-changing frequency, and speed, thereby providing a personalized driving experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a unified autonomous driving strategy is employed, then the system complexity is reduced and ease of operation is improved, but the adaptability to different user driving habits deteriorates
Solution Approach 1:
The system performs preliminary learning of user driving habits during manual driving phases, storing behavioral patterns and preferences in advance. When autonomous driving mode is activated, the pre-learned habits are retrieved and applied, allowing the system to adapt to user preferences without real-time complexity. This resolves the contradiction by preparing adaptability data beforehand, so the autonomous system can personalize driving behavior without increasing operational complexity during autonomous mode.
2Adaptability or versatility
If autonomous driving system learns and adapts to individual user habits, then the adaptability and user experience are improved, but the device complexity and data processing requirements increase
Solution Approach 1:
The system segments driving behavior into distinct可学习 components such as steering patterns, acceleration preferences, braking habits, and lane-changing behaviors. Each segment is learned and stored separately, allowing the system to adapt to user habits without processing the entire driving scenario as one complex task. This segmentation reduces the computational burden and device complexity while maintaining high adaptability to individual user preferences.
3Reliability
If fixed parameters are used for autonomous driving, then the reliability and safety are improved through consistent behavior, but the user satisfaction and personalized experience deteriorate
Solution Approach 1:
The system transitions from static fixed parameters to dynamic adaptive parameters that evolve based on learned user habits. The autonomous driving controller dynamically adjusts driving behavior parameters such as following distance, speed adjustments, and maneuver timing based on the stored user profile. This dynamic adaptation maintains reliability through consistent application of learned patterns while improving adaptability to individual user preferences, resolving the contradiction between reliable consistent behavior and personalized experience.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
The present application discloses a method, an apparatus and a device for determining a behavioral driving habit and controlling vehicle driving, which relates to an autonomous driving technology in the field of artificial intelligence. A specific implementation is to: acquire driving behavior-related data during a user's manual driving a first vehicle on a road and map data (S301); and determine, according to the driving behavior-related data and the map data described above, an association relationship between driving parameters used during the user's manual driving the first vehicle (S302); where the association relationship between the driving parameters represents a behavioral driving habit of the user. In this way, an autonomous driving strategy of a second vehicle may be updated according to the behavioral driving habit of the user, so that personalized autonomous driving requirements from different users are met.