Virtual Potential Field Evasive Steering Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing collision avoidance systems in vehicles are limited to automatic braking and lack the capability to provide combined automatic braking and steering to effectively avoid collisions when lane markings are not present.
Innovation Solution
A system and method that calculates a virtual target path using a potential field process employing a quadratic polynomial function, allowing for evasive steering around a target object by separating scan points from sensors into target and other objects, and determining a mesh grid to identify a local minimum point for the steering path, which is then connected using a least-square method.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If collision avoidance systems use automatic braking only, then the system simplicity is maintained, but the collision avoidance effectiveness is insufficient when lane markings are not present
Solution Approach 1:
The system segments the problem of collision avoidance into two independent modules: automatic braking for longitudinal control and virtual target path calculation for lateral steering control. This segmentation allows the system to add steering functionality without completely redesigning the existing braking system, thereby improving collision avoidance effectiveness while managing system complexity through modular architecture
Solution Approach 2:
The patent introduces a virtual target path as an intermediary computational element that mediates between sensor data and steering control. This virtual path, calculated using potential field methods and quadratic polynomial functions, serves as a intermediate representation that guides the evasive steering maneuver without requiring direct lane marking detection, thus enhancing avoidance capability while maintaining system manageability
2Measurement precision
If the system relies on lane markings for steering guidance, then the steering path accuracy is improved, but the system adaptability to environments without lane markings deteriorates
Solution Approach 1:
The virtual target path calculation system serves multiple functions: it provides steering guidance in environments with lane markings, operates effectively in environments without lane markings, and adapts to various road conditions and obstacle configurations. This multi-functionality is achieved through potential field methods that generate avoidance paths based on obstacle detection rather than relying on specific environmental features like lane markings
Solution Approach 2:
The system changes the fundamental parameter for path guidance from lane marking coordinates to virtual potential field parameters. By using quadratic polynomial functions to model the potential field around obstacles and calculating the gradient descent path, the system achieves accurate steering guidance based on obstacle position and vehicle dynamics rather than environmental markers, thereby improving adaptability to diverse environments
Data Source
AI summary
A system and method for calculating a virtual target path that is used to calculate an evasive steering path around a target object, such as a target vehicle, stopped in front of a subject vehicle. The method includes determining a potential field using a plurality of scan points that is a summation of two-dimensional Gaussian functions, where each Gaussian function has center defined by target object scan points and other object scan points. The method identifies a mesh grid in an X-Y plane where the mesh grid includes mesh grid points at locations where X and Y plane lines cross. The method identifies a local minimum point of the potential field for each X-plane line at each mesh grid point along the Y-plane crossing that X-plane line, where the local minimum point is a curve point. The method then connects the curve points to define the target path.