Driving Assist Risk Field for Probabilistic Collision Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driving assist systems overestimate collision risks when assuming targets move perpendicularly to the roadway, leading to excessive or unnecessary risk avoidance control operations.
Innovation Solution
A driving assist system that calculates a risk field by considering multiple patterns of target state parameters, including expected direction and speed, to accurately assess collision risks and execute risk avoidance control, such as steering and deceleration, based on a highly accurate representation of the risk of collision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If the system assumes targets move perpendicularly to the roadway at a predetermined speed, then the risk calculation is simplified, but the risk of collision is overestimated leading to excessive risk avoidance control operations
Solution Approach 1:
The system dynamically adjusts the target state parameters based on the detected target's actual movement characteristics. Instead of using a fixed perpendicular movement assumption, the system adapts the expected direction and speed parameters to match the target's observed behavior, thereby reducing overestimation while maintaining computational efficiency.
Solution Approach 2:
The system changes the parameters used in risk calculation from fixed predetermined values to variable values that reflect actual target behavior. By adjusting the expected direction and speed parameters based on detected target movement patterns, the system achieves more accurate risk assessment without significantly increasing computational complexity.
2Measurement precision
If the system uses multiple patterns of target state parameters to accurately assess collision risks, then the accuracy of risk assessment is improved, but the computational complexity increases
Solution Approach 1:
The system applies partial action by selecting and applying only the most relevant target state parameters based on the specific situation. Instead of exhaustively calculating all possible parameter combinations, the system focuses on the key parameters that have the greatest impact on collision risk, thereby maintaining accuracy while reducing computational burden.
Solution Approach 2:
The system segments the risk calculation process into distinct stages: first detecting target movement characteristics, then selecting appropriate state parameters, and finally calculating risk values. This segmentation allows the system to handle complex calculations in manageable steps, improving accuracy without overwhelming computational resources.
Data Source
AI summary
A driving assist system executes risk avoidance control for reducing a risk of collision with a target existing ahead of a vehicle. A vehicle state parameter includes imaginary relative position and velocity of the vehicle. A target state parameter includes expected direction and speed of movement the target. A risk value is expressed by a function of an estimated collision speed between the vehicle defined by the vehicle state parameter and the target defined by the target state parameter. The driving assist system sets multiple patterns of the target state parameter and sets a probability of each target state parameter. A partial risk value is the risk value when each target state parameter is used. A final risk value applied to the risk avoidance control is a sum of products of the probability and the partial risk value with respect to the multiple patterns of target state parameter.