Personalized Lane Planning Using Human Driving Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving technologies fail to address the variability in human driving behaviors and passenger preferences, leading to inadequate lane planning and control in autonomous vehicles.
Innovation Solution
The development of a system that uses sensor data and personalized lane control models based on recorded human driving data to detect the current lane and passenger presence, predicting operational capabilities and adapting vehicle control to mimic human-like behavior in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional autonomous driving planning modules use generic vehicle kinematic models and feedback controllers, then the system can operate with simple control logic, but the lane planning and control behavior does not reflect human driving preferences and variability
Solution Approach 1:
The system performs preliminary action by collecting and storing recorded human driving data before operation, and by generating personalized lane control models in advance based on this data. This allows the system to adapt to human preferences without computing complex models in real-time, resolving the contradiction between adaptability and complexity.
Solution Approach 2:
The system uses copying by creating personalized lane control models that replicate human driving behavior patterns from recorded data. Instead of implementing complex real-time analysis of human preferences, the system copies proven human driving patterns into predictive models that guide autonomous vehicle control, achieving human-like adaptability with manageable complexity.
2Reliability
If the system uses personalized lane control models based on recorded human driving data, then lane planning reflects human-like behavior and passenger preferences, but the system complexity and computational requirements increase
Solution Approach 1:
The system performs preliminary action by collecting and storing recorded human driving data before operation, and by generating personalized lane control models in advance based on this data. This allows the system to adapt to human preferences without computing complex models in real-time, resolving the contradiction between adaptability and complexity.
Solution Approach 2:
The system uses feedback by continuously monitoring actual lane control outcomes and using this information to refine and update personalized lane control models. This iterative feedback process improves lane planning accuracy over time while keeping the computational burden manageable by building on existing models rather than recreating them from scratch.
3Adaptability or versatility
If the autonomous vehicle system collects and processes recorded human driving data and sensor data in real-time, then it can provide personalized and adaptive lane control, but the data processing time and computational load increase
Solution Approach 1:
The system performs preliminary action by collecting and storing recorded human driving data before operation, and by generating personalized lane control models in advance based on this data. This allows the system to adapt to human preferences without computing complex models in real-time, resolving the contradiction between adaptability and complexity.
Solution Approach 2:
The system uses copying by creating personalized lane control models that replicate human driving behavior patterns from recorded data. Instead of implementing complex real-time analysis of human preferences, the system copies proven human driving patterns into predictive models that guide autonomous vehicle control, achieving human-like adaptability with manageable complexity.
4Measurement precision
If the system integrates multiple sensor data sources and personalized models for lane detection and control, then measurement precision and control accuracy improve, but the device complexity and integration requirements increase
Solution Approach 1:
The system applies merging by integrating sensor data processing and personalized lane control modeling into a unified planning module. This consolidation improves measurement precision through coordinated multi-sensor operation while managing device complexity by providing a single integration interface and centralized control logic.
Data Source
AI summary
The present teaching relates to method, system, medium, and implementation of lane planning in an autonomous vehicle. Sensor data are received that capture ground images of a road the autonomous vehicle is on. Based on the sensor data, a current lane of the road that autonomous vehicle is currently occupying is detected. Information indicating presence of a passenger in the vehicle is obtained and used to retrieve a personalized lane control model related to the passenger. Lane control for the autonomous vehicle is planned based on the detected current lane and self-aware capability parameters in accordance with the personalized lane control model. The self-aware capability parameters are used to predict operational capability of the autonomous vehicle with respect to a current location of the autonomous vehicle. The personalized lane control model is generated based on recorded human driving data.