Adaptive Occupancy Grid Map Updating Weights
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing occupancy grid map generation techniques face challenges in appropriately setting the updating width for occupancy probabilities, leading to either large probability changes resulting in false positives or slow identification of targets due to small changes.
Innovation Solution
An occupancy grid map generation device that acquires detection result data and map data to calculate updating weights for occupancy probabilities, allowing for controlled updates based on the degree of match between detection results and map data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the updating width for occupancy probability is increased, then the target identification speed is improved, but false detections increase due to large probability changes
Solution Approach 1:
The patent applies dynamics by making the updating width adaptive rather than fixed. The updating width is dynamically adjusted based on the consistency between detection result data and map data, allowing the system to automatically optimize between identification speed and false detection rate according to current environmental conditions
Solution Approach 2:
The patent changes the parameter of updating width based on data consistency. When detection results match map data well, a larger updating width is used to speed up target identification. When consistency is poor, a smaller updating width is used to reduce false detections, thus optimizing performance across different scenarios
2Reliability
If the updating width for occupancy probability is decreased, then false detections are reduced, but target identification becomes slower
Solution Approach 1:
The system dynamically adjusts the updating width based on real-time consistency assessment between detection results and map data, preventing the need to maintain a consistently small updating width that would slow down target identification in reliable conditions
Solution Approach 2:
The updating width parameter is changed according to data consistency metrics, allowing the system to use smaller widths only when necessary to reduce false detections, while using larger widths when data consistency is high to maintain fast target identification
3Device complexity
If fixed updating width is used for occupancy probability, then the system complexity is reduced, but the system cannot adapt to varying environmental conditions
Solution Approach 1:
The system performs self-adjustment by automatically determining the appropriate updating width based on the consistency between detection results and map data. This self-service mechanism allows the system to adapt to varying environmental conditions without requiring complex external control or manual intervention
Solution Approach 2:
The system uses feedback from the consistency assessment between detection result data and map data to adjust the updating width. This feedback loop enables the system to adapt to environmental conditions by learning from the agreement or disagreement between sensor data and map information
Data Source
AI summary
In an occupancy grid map generation device for generating an occupancy grid map that indicates, for each of cells of a grid into which a region is divided, an occupancy probability that an object occupies the cell, an occupancy probability updating unit is configured to, based detection result data of an object therearound, successively update the occupancy probability for each of the cells calculated at a previous time to calculate a latest occupancy probability. An updating weight calculation unit is configured to acquire data about presence or absence of an object in each of the cells therearound based on map data, and determine a weight of the detection result data used by the occupancy probability updating unit to update the occupancy probability for the cell, based on a degree of match between the data about presence or absence of an object in the cell and the detection result data.