Lane Change Intention Estimation Using Driver Risk Adaptability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driver assistance systems struggle to accurately determine the lane changing intention of surrounding vehicles, particularly due to the lack of consideration for individual driver habits, leading to potential discomfort and increased collision risks for host vehicles.
Innovation Solution
A method and system for estimating the lane changing intention of a target vehicle using a probability-based risk adaptability model, which accumulates driving risk data over a predetermined time and generates a risk adaptability model to estimate the target vehicle's lane changing intention based on its driving habits.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If lane changing intention is estimated using only position, speed, and heading angle of surrounding vehicles, then the estimation process is simple, but the accuracy is insufficient because individual driver habits are not considered
Solution Approach 1:
The system performs preliminary actions by accumulating driving risk data over time before making lane changing intention estimation. It collects position, speed, and heading angle data during straight driving phases and stores this information in advance, then uses the accumulated data to generate risk adaptability models that capture individual driver habits, thereby improving estimation accuracy without requiring complex real-time processing
Solution Approach 2:
The system changes parameters by transitioning from using only basic motion parameters (position, speed, heading angle) to incorporating derived parameters such as driving risk data and risk adaptability model scores. This allows the system to capture individual driver behavior patterns and improve lane changing intention estimation accuracy while managing complexity through structured data transformation
2Measurement precision
If driving risk data is accumulated for a predetermined time to generate risk adaptability model, then the estimation accuracy improves by considering driver habits, but the response time increases
Solution Approach 1:
The system accumulates driving risk data during straight driving phases as a preliminary action, building up a database of driver behavior patterns before estimation is needed. This preliminary data collection enables the generation of personalized risk adaptability models that improve accuracy while allowing the system to respond quickly once the model is established
Solution Approach 2:
The system dynamically adjusts its operation by monitoring driving phases and switching between data accumulation mode (during straight driving) and estimation mode (when lane changing intention needs to be determined). This dynamic approach allows the system to balance data collection requirements with real-time response needs
3Reliability
If the system detects and responds to lane changes by surrounding vehicles, then collision risk is reduced, but driver comfort decreases due to frequent braking and direction changes
Solution Approach 1:
The system applies preliminary anti-action by estimating lane changing intention before the actual lane change occurs. By using the risk adaptability model to predict which surrounding vehicles are likely to change lanes, the host vehicle can take preventive measures such as gentle steering adjustments or speed modifications in advance, avoiding sudden braking or sharp direction changes that would discomfort the driver while still preventing collisions
Data Source
AI summary
A method and system for estimating lane changing intention of a target vehicle is provided, and a method for estimating lane changing intention of a target vehicle according to an embodiment of the present disclosure comprises: detecting the target vehicle and at least one peripheral vehicle of the target vehicle using at least one sensor installed at a host vehicle; accumulating driving risk data of the target vehicle with respect to at least one peripheral vehicle while the target vehicle is driving straight; determining whether the driving risk data has been accumulated for a predetermined time; if the driving risk data has been accumulated for the predetermined time, generating a risk adaptability model based on the accumulated driving risk data; estimating the lane changing intention of the target vehicle based on the generated risk adaptability model; and controlling the host vehicle based on the lane changing intention of the target vehicle.