Local-Sensor Lane Change Path Matching Without GPS Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing assisted driving systems face challenges in performing lane changes efficiently without relying on costly global localization tools like GPS receivers or high-definition maps, which may not be available in all areas.
Innovation Solution
The system performs a computer-implemented method that defines a transformation matrix between the origin of a lane change and multiple points along a global path, using local information from sensors like cameras and lidars to match parametric representations of the target lane, allowing the vehicle to change lanes based solely on local data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If global localization tools like GPS receivers and high-definition maps are used for lane changing, then lane changing accuracy and reliability are improved, but system cost and device complexity increase
Solution Approach 1:
The patent extracts the essential function of global localization (determining vehicle position and orientation) and implements it through local sensor data processing only. By removing dependence on GPS receivers and high-definition maps, the system achieves lane changing capability using only locally available sensor information from cameras and lidars, thereby reducing system cost and device complexity while maintaining operational reliability.
Solution Approach 2:
The patent creates a virtual representation of the target lane by matching parametric equations to sensor-detected lane markings. This virtual model serves as a local substitute for global localization data, enabling the vehicle to plan and execute lane changes accurately without requiring expensive global positioning infrastructure.
2Measurement precision
If global localization tools are used for lane changing, then lane changing precision is improved, but availability and adaptability to different areas decrease
Solution Approach 1:
The system performs self-localization by using its own sensors (cameras and lidars) to detect and interpret lane markings in the environment. This self-service approach eliminates dependence on external global localization infrastructure like GPS and high-definition maps, enabling the vehicle to perform lane changes with precision in any area where lane markings are visible, thereby significantly improving area availability and adaptability.
3Device complexity
If local information only is used for lane changing, then system cost and availability are improved, but measurement precision and reliability may worsen
Solution Approach 1:
The patent performs preliminary processing of sensor data to extract lane marking information and fit parametric equations to the detected features before lane change execution. By pre-processing and modeling the local environmental data, the system compensates for the lack of global localization tools, maintaining measurement precision while using only cost-effective local sensors.
Solution Approach 2:
The system creates an accurate virtual model of the target lane by matching parametric equations to sensor-detected lane markings. This virtual representation serves as a precise reference for lane change planning, compensating for the absence of global localization data and maintaining lane changing precision through sophisticated local data processing.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computer-implemented method comprises: initiating, by an assisted-driving system that is controlling motion of a vehicle, a lane change of the vehicle from an ego lane to a target lane, the lane change to be performed based only on local information of the vehicle; defining, by the assisted-driving system, a parametric representation of the target lane, the parametric representation based on first waypoints of the target lane; receiving, by the assisted-driving system and during the lane change, a first output of a perception component of the vehicle, the first output being the local information and reflecting second waypoints of the target lane; performing, by the assisted-driving system, a comparison based on the first output and the parametric representation; and providing, by the assisted-driving system, references of a first global path to controllers of the vehicle for actuating the lane change, the references selected based on the comparison. The invention exploits that the representation of the target lane in the respective local frame changes while the vehicle moves.