Vehicle Sensor Positioning from Lane Geometry and Boundary Offsets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor systems in vehicles with unknown positions relative to the vehicle itself cannot accurately derive trajectories due to unknown positioning, leading to degraded accuracy in map encoding, behavior planning, and machine learning model training.
Innovation Solution
Techniques for determining the lateral, longitudinal, and vertical positioning of vehicle-based sensor systems relative to the vehicle using sensor data and map information, allowing for precise trajectory derivation and improved data utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If sensor systems are installed without controlled positioning in vehicles, then ease of installation is improved, but measurement precision of sensor position relative to vehicle deteriorates
Solution Approach 1:
The system performs self-calibration by automatically determining sensor positions using vehicle trajectory data and map information without requiring manual positioning or specialized installation equipment. The sensor system serves itself to establish its own positional reference frame through environmental observation and computational geometry.
Solution Approach 2:
The system transforms the problem from physical positioning to computational positioning by changing parameters from fixed installation coordinates to dynamically calculated positions based on trajectory analysis, lane geometry, and sensor-lane boundary relationships.
2Device complexity
If sensor positions are unknown, then device complexity is reduced, but trajectory derivation accuracy deteriorates
Solution Approach 1:
The system introduces map information and lane geometry data as intermediary elements that mediate between the sensor system and vehicle reference frame. These intermediaries provide the geometric constraints needed to calculate sensor positions without direct physical measurement or complex positioning hardware.
Solution Approach 2:
The patent replaces mechanical positioning systems (such as GPS, inertial sensors, or physical measurement devices) with a computational approach using trajectory analysis and geometric reasoning to determine sensor positions and derive accurate vehicle trajectories.
3Productivity
If sensor data is used without position correction, then productivity is improved by immediate data utilization, but map encoding accuracy deteriorates
Solution Approach 1:
The system performs preliminary positioning calculations and sensor location determination before the sensor data is used for map encoding or trajectory derivation. This preliminary action establishes the correct reference frame transformation, ensuring that subsequent data utilization maintains high accuracy without requiring retroactive corrections.
Data Source
AI summary
Determining positioning of a sensor system associated with a vehicle involves: (i) identifying a given time when the vehicle was driving in a lane having substantially-straight lane geometry, (ii) inferring that, because the lane had substantially-straight lane geometry at the given time, the vehicle was laterally positioned in alignment with a lateral centerline of the lane at the given time, (iii) detecting a lane boundary of the lane in which the vehicle was driving at the given time, (iv) determining, at the given time, a first lateral distance between the lane boundary and the vehicle's associated sensor system and a second lateral distance between the lane boundary and the lateral centerline of the lane, and (v) based on the first and second lateral distances, determining a given measure of a lateral offset between the vehicle's associated sensor system and the lateral center of the vehicle for the given time.