Driving Environment Virtualization Using Multi-Vehicle Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current driver assistance systems face challenges in accurately sensing and sharing knowledge of the driving environment due to incomplete or inaccurate data from on-board sensors, leading to issues like missed objects or 'ghost' objects, and existing inter-vehicle communication methods provide limited and abstract information.
Innovation Solution
A device and method for virtualizing the driving environment by acquiring and compressing position and sensing data from multiple nodes within communication networks, constructing a scene using topology and image construction devices, and fusing identified data to create a comprehensive and accurate virtual representation of the environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If on-board sensors (radar, lidar, camera) are used to acquire driving environment data, then the vehicle can detect objects adjacent to it, but the sensing data may be incomplete or inaccurate (blocked objects missed, ghost objects generated)
Solution Approach 1:
The patent merges sensing data from multiple vehicles through inter-vehicle communication networks. By combining detection results from different spatial perspectives, the system compensates for individual sensor limitations, eliminating blocked objects and ghost objects through data fusion and cross-validation.
2Loss of information
If sensing data is exchanged between vehicles via inter-vehicle communication network, then knowledge of driving environment can be shared, but the shared knowledge remains abstract and limited
Solution Approach 1:
The patent creates virtual copies of the physical driving environment by constructing virtual scenes from exchanged sensing data. These virtual scenes include virtual objects with spatial positions, dimensions, and attributes, providing intuitive and comprehensive environmental representation without requiring direct physical sensing from each vehicle.
3Loss of energy
If compressed sensing data with coordinate sets and layer indices is transmitted, then network overhead is reduced, but data decompression and processing is required
Solution Approach 1:
The patent segments sensing data into compressed formats using coordinate sets representing object edges and layer indices for hierarchical representation. This segmentation enables efficient data transmission by storing only essential geometric features rather than complete point cloud data, reducing network overhead while maintaining reconstruction capability.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
A device for virtualizing a driving environment (1010) surrounding a first node, which includes: a data acquisition device (201), configured to acquire position data of the first node, position data and sensing data of at least one second node, where the at least one second node and the first node are in a first communication network; and a scene construction device (203), configured to construct a scene virtualizing the driving environment surrounding the first node based on the position data of the fist node and the at least one second node, and on the sensing data of the at least one second node. Accordingly, by utilizing position data and sensor data of a node, a scene for virtualizing a driving environment can be constructed in real time for a driver, which improves driving safety.