Dynamic Occupancy Grid Fusion for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous and semi-autonomous vehicle systems face challenges in accurately determining occupancy and velocity in dynamic environments, particularly due to limitations in integrating radar and camera sensor data effectively.
Innovation Solution
The system obtains radar-based and camera-based occupancy grids, each comprising cells with occupancy probabilities and velocities, and then determines a dynamic occupancy grid by fusing these two datasets, allowing for improved accuracy in tracking vehicles and objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radar sensor measurements are used to determine occupancy grids, then velocity information can be obtained, but measurement precision of occupancy probability is insufficient
Solution Approach 1:
The patent combines radar occupancy grids (providing velocity information) with camera occupancy grids (providing precise occupancy detection) into a fused occupancy grid. This merging allows the system to simultaneously obtain both accurate occupancy probabilities and velocity information that neither sensor could provide alone with sufficient precision.
2Measurement precision
If camera measurements are used to determine occupancy grids, then occupancy probability precision is improved, but velocity information is lost
Solution Approach 1:
The system fuses camera-based occupancy grids with radar-based occupancy grids. The camera provides precise occupancy detection while the radar supplies velocity data. By combining these complementary data sources, the system recovers velocity information that would otherwise be lost when using camera measurements alone.
3Measurement precision
If radar and camera sensor data are integrated, then occupancy grid accuracy is improved, but device complexity increases
Solution Approach 1:
The patent uses an occupancy grid representation as an intermediary data structure to facilitate the integration of radar and camera sensor data. By converting sensor measurements into a common occupancy grid format with standardized cell structures containing probability and velocity information, the system simplifies the integration process and manages complexity through this mediating representation.
Data Source
AI summary
A dynamic occupancy grid determination method includes: obtaining, at an apparatus, at least one radar-based occupancy grid based on radar sensor measurements, each of the at least one radar-based occupancy grid comprising a plurality of first cells, each cell of the plurality of first cells having a corresponding first occupancy probability and first velocity; obtaining, at the apparatus, at least one camera-based occupancy grid based on camera measurements, each of the at least one camera-based occupancy grid comprising a plurality of second cells, each cell of the plurality of second cells having a corresponding second occupancy probability and second velocity; and determining, at the apparatus, a dynamic occupancy grid by analyzing the at least one radar-based occupancy grid and the at least one camera-based occupancy grid.