Dynamic Grid Collision Free Space Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advanced driver assistance systems require a grid-based representation of collision-free space in front of a host vehicle, but existing methods using polar coordinates increase computational effort due to the need for transformations.
Innovation Solution
A dynamic grid is formed in front of the host vehicle based on detected limiting points, with each cell determined to be obstacle-free or not, reducing computational effort by adapting to the lane's course and providing a more useful representation for applications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a polygon representation in polar coordinates is used to define the collision free space, then the representation is simple and continuous, but the computational effort increases when transforming to grid-based representation for discrete applications
Solution Approach 1:
The patent performs the coordinate transformation from polar to grid-based representation in advance, during the detection phase, rather than transforming on-demand for each application. The limiting points are detected and stored in a preprocessed form that can be directly used by multiple discrete applications, eliminating repeated transformation computations.
Solution Approach 2:
The patent dynamically adapts the grid structure to the detected limiting points by creating a bounding box that encompasses all limiting points and dividing it into a variable number of cells based on the spatial distribution of points. This dynamic grid creation optimizes the balance between resolution and computational efficiency for each specific scene.
2Adaptability or versatility
If a detailed grid-based representation is created for each application from polar coordinates, then the information is highly useful for discrete applications, but the computational effort and processing time increase significantly
Solution Approach 1:
The patent creates a universal grid-based representation of the collision free space that can be used by multiple different discrete applications (e.g., path planning, obstacle detection, navigation). Instead of creating separate representations for each application, a single grid structure serves multiple purposes, reducing redundant computations.
Solution Approach 2:
The grid-based representation is prepared in advance during the detection phase, so that when discrete applications need this information, it is already available in the required format. This preliminary preparation eliminates the need for real-time transformation during critical application execution.
3Measurement precision
If the collision free space is represented as a continuous polygon, then the boundary information is precise, but discrete applications require additional transformation steps to obtain grid cell information
Solution Approach 1:
The patent segments the continuous collision free space into discrete grid cells that align with the limiting points. By dividing the bounding box into a matrix of cells and determining which cells are fully contained within the collision free space, the system transforms continuous boundary information into discrete cell information that is directly usable by applications requiring grid-based data.
Solution Approach 2:
The patent creates a discrete copy of the collision free space information in grid cell format, which is a simplified representation that preserves the essential boundary information in a form suitable for discrete applications. This copy allows applications to work with simplified cell-based data rather than complex continuous polygon mathematics.
Data Source
AI summary
A computer implemented method is provided for determining a collision free space in front of a host vehicle. A plurality of limiting points is detected via a detection system of the host vehicle, wherein each limiting point is located at a respective obstacle free distance with respect to the vehicle. A dynamic grid is formed in front of the host vehicle, wherein the dynamic grid is based on the course of a lane being determined in front of the host vehicle via the detection system of the host vehicle, and wherein the dynamic grid comprises a plurality of cells. An obstacle free subset of the cells is determined based on the plurality of limiting points, wherein the obstacle free subset of the cells defines the collision free space in front of a host vehicle.