Radar Occupancy Grid Refinement for Reliable Obstacle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control and assistance systems rely on sensor data from cameras, radar, and lidar systems, but there is a need for improvements in navigation and object detection to enhance driving assistance functions.
Innovation Solution
A computer-implemented method for generating a refined three-dimensional occupancy grid map and feature grid maps using radar point sensor data, which are then processed by a convolutional neural network to improve the quality of the grid maps for use in vehicle assistance systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensor data processing methods are used for object detection, then the system complexity is low, but the detection accuracy and reliability are insufficient
Solution Approach 1:
The patent segments the environment representation into multiple feature grid maps, each capturing specific characteristics (occupancy, radial velocity, range, RCS). This segmentation allows the system to process different features separately and combine them, improving detection accuracy while maintaining manageable system complexity through modular processing.
Solution Approach 2:
The patent transitions from traditional 2D sensor data processing to 3D occupancy grid maps with additional feature dimensions. By adding spatial depth and feature dimensions (velocity, range, RCS), the system achieves more accurate object detection and classification without proportionally increasing complexity, as the additional dimensions are processed through systematic algorithms.
2Reliability
If multiple sensor systems (camera, radar, lidar) are integrated for comprehensive environment perception, then the detection reliability improves, but the device complexity and processing requirements increase
Solution Approach 1:
The patent makes the radar sensor system multi-functional by extracting multiple types of information (occupancy, velocity, range, RCS) from a single sensor source. This universality allows the system to achieve comprehensive environment perception similar to multiple sensor systems, but with reduced complexity by relying primarily on radar capabilities.
Solution Approach 2:
The patent creates feature grid maps that are analogous to what multiple sensor systems would produce independently. By generating separate grid maps for different features (occupancy, velocity, range, RCS) from radar data, the system replicates the functional output of multiple sensors without the hardware complexity, achieving similar detection reliability.
3Manufacturing precision
If high-resolution grid maps are generated for detailed environment representation, then the navigation accuracy improves, but the data processing time and computational load increase
Solution Approach 1:
The patent segments the complex high-resolution grid map generation into multiple independent feature grid maps (occupancy, velocity, range, RCS). Each feature map is generated and processed separately, allowing parallel computation and reducing the overall processing time while maintaining high resolution and accuracy in the final integrated representation.
Data Source
AI summary
A computer-implemented method for driving assistance in a vehicle. The method includes generating, based on radar point sensor data of an environment of the vehicle, a three-dimensional occupancy grid map (3D OGM). The method includes generating, based on the radar point sensor data, a number of feature grid maps (FGMs). A respective feature dimension of each of the FGMs corresponds to a feature of the radar point sensor data. The method includes generating, based on the 3D OGM and the number of FGMs, a refined occupancy grid (OGM). The method includes providing the refined OGM for usage by an assistance system of the vehicle.