Sensor-Fused Path Planning Without High-Precision Vector Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current self-driving technologies face challenges in accurately detecting distances to intersections using image processing, leading to potential safety issues and requiring high-precision vector maps that are costly and labor-intensive to create, with varying formats across regions.
Innovation Solution
A path planning method and system that utilizes a road image and distance sensor in conjunction with specific algorithms to create a road distance point-cloud map, fuse camera images with point-cloud data, and segment road lines, allowing for precise path detection and planning without the need for high-precision vector maps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-precision vector maps are used to improve path detection precision, then measurement precision is improved, but device complexity and manufacturing cost increase due to complex vector marking software and government cooperation
Solution Approach 1:
The patent segments the road detection task into two parts: using simple image processing to detect road line positions and using distance sensor data to measure actual distances. This segmentation allows the system to achieve high precision without requiring complex vector maps, as each component performs a simplified function that can be accurately executed independently.
Solution Approach 2:
The patent creates a virtual road model by copying and integrating data from simple image processing results and distance sensor measurements. This virtual model replicates the functionality of high-precision vector maps but is generated dynamically from inexpensive sensors, eliminating the need for complex pre-existing map data while achieving comparable or superior accuracy.
2Measurement precision
If high-precision vector maps are used to improve path detection precision, then measurement precision is improved, but manufacturing cost increases due to labor-intensive map creation
Solution Approach 1:
The system performs self-service by using the vehicle's own distance sensors and cameras to generate accurate path information in real-time. Instead of relying on externally created and maintained vector maps that require continuous manual updates and government cooperation, the system autonomously creates its own navigation data from onboard sensors, eliminating ongoing manufacturing and maintenance costs.
Solution Approach 2:
The patent changes the fundamental parameters of the system from using pre-existing high-precision map data to using real-time sensor measurements. By shifting from static map data to dynamic sensor-based measurement, the system achieves high precision without the manufacturing burden of creating and maintaining detailed vector maps, as the measurement process itself becomes the source of accuracy.
3Device complexity
If image processing alone is used to detect front path, then device complexity is reduced, but measurement precision deteriorates due to inaccurate distance estimation
Solution Approach 1:
The patent merges image processing results with distance sensor measurements to achieve accurate path detection. The image processing provides road line positions while the distance sensor provides accurate range data. By combining these two simple components, the system achieves both low device complexity and high measurement precision, as the strengths of each component compensate for the weaknesses of the other.
Solution Approach 2:
The patent introduces a data fusion algorithm as an intermediary that processes and integrates information from image processing and distance sensing. This intermediary component coordinates the data from both sources, reconciling their different measurement types and formats into unified, accurate path information, thereby enabling the simple components to work together effectively.
Data Source
AI summary
A path planning system includes an image-capturing device, a point-cloud map-retrieving device, and a processing device. The image-capturing device captures a first and a second camera road image. The point-cloud map-retrieving device retrieves distance data points to create a road distance point-cloud map. The processing device receives the road distance point-cloud map and the first and second camera road images, calibrates and fuses those to generate a road camera point-cloud fusion map, and then determines the road-line information of the second camera road image to generate a road-segmented map. The road-segmented map and the road camera point-cloud fusion map are fused. The distance data of the road-segmented map are obtained according to distance data points. A front driving path for the target road is planned according to the distance data.


