Vehicle-Roadside Sensor Fusion for Extended Autonomous Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Self-driving vehicles face limitations in road environment sensing due to the narrow sensing range of vehicle sensing apparatuses, which is insufficient for effective navigation and safety.
Innovation Solution
A data fusion method that combines roadside sensing data with vehicle sensing data using a fusion formula, extending the sensing range by integrating confidence factors and utilizing a deviation network for matching and evaluation, thereby enhancing the accuracy and coverage of environmental perception.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If only vehicle sensing apparatus is used for road environment sensing, then the device complexity is reduced, but the sensing range is narrow and insufficient for self-driving requirements
Solution Approach 1:
The patent merges vehicle-mounted sensing apparatus and roadside sensing apparatus into a coordinated sensing system. The roadside sensing apparatus extends the overall sensing range, while the vehicle sensing apparatus provides complementary close-range detection, together forming a comprehensive sensing network that covers both far and near ranges.
Solution Approach 2:
The patent introduces a data fusion device as an intermediary that receives sensing data from both vehicle-mounted and roadside sensing apparatus, performs data association and fusion processing, and outputs integrated sensing results. This mediator coordinates the two sensing systems and resolves the complexity of direct integration.
2Measurement precision
If vehicle sensing apparatus operates independently, then the system is simple, but the measurement precision and confidence of environmental perception are insufficient
Solution Approach 1:
The patent implements a feedback mechanism where the data fusion device associates vehicle sensing data with roadside sensing data, evaluates the confidence of each data source, and uses this feedback to weight and fuse the data appropriately. This feedback loop continuously optimizes the sensing accuracy by leveraging the strengths of each sensing apparatus.
Solution Approach 2:
The patent creates a composite sensing system that combines data from multiple sensing apparatus with different characteristics. By fusing vehicle-mounted sensing data (good for close-range, dynamic objects) with roadside sensing data (good for far-range, static objects), the system achieves superior overall measurement precision comparable to composite material advantages.
3Area of stationary object
If roadside sensing apparatus is added to extend sensing range, then the sensing coverage is improved, but the device complexity and data processing load increase
Solution Approach 1:
The patent segments the sensing system into independent functional modules: vehicle-mounted sensing apparatus, roadside sensing apparatus, and data fusion device. Each module operates independently with its own processing capabilities, and the data fusion device coordinates them through standardized data interfaces, reducing overall system integration complexity.
Solution Approach 2:
The data fusion device is designed with universal functionality to handle various types of sensing data from different apparatus. It performs multiple functions including data association, confidence evaluation, data fusion, and result output, making it adaptable to different sensing configurations and reducing the need for specialized integration for each sensing apparatus.
Data Source
AI summary
This application discloses a data fusion method and a related device. The method includes: obtaining vehicle sensing data, where the vehicle sensing data is obtained by a vehicle sensing apparatus by sensing a road environment in a sensing range by using a vehicle sensor; obtaining roadside sensing data, where the roadside sensing data is obtained by a roadside sensing apparatus by sensing a road environment in a sensing range by using a roadside sensor; and fusing the vehicle sensing data and the roadside sensing data by using a fusion formula, to obtain a first fusion result. According to the foregoing solution, overlapping can be implemented between the sensing range of the roadside sensing apparatus and the sensing range of the vehicle sensing apparatus can be implemented, so that the sensing range is effectively extended.