Vehicle Positioning via Probabilistic Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated vehicles face challenges in reliably determining their position, especially in environments where structural separation from non-operating areas is not possible, leading to potential safety hazards due to inaccurate localization, particularly for large and fast-moving vehicles that may not detect barriers in time.
Innovation Solution
A method utilizing a combination of global positioning systems, inertial measurement units, and odometry systems to determine a vehicle's absolute and relative positions, calculating position certainty based on sensor accuracy, and defining a tolerance range to ensure safe operation, with additional systems like RFID transponders, LIDAR-SLAM, and cameras providing supplementary position data for enhanced reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple positioning systems (GNSS, inertial measurement unit, odometry system) are used to determine position, then position reliability is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple positioning systems (GNSS, inertial measurement unit, and odometry system) into a unified positioning architecture that integrates their outputs through a probabilistic model. This merging approach allows the system to leverage the strengths of each individual system while maintaining a manageable overall complexity through standardized integration protocols and a common evaluation framework.
Solution Approach 2:
The patent creates a universal positioning system that can operate with any combination of positioning subsystems. The probabilistic evaluation model serves as a multi-functional interface that processes inputs from different sensor types and provides a unified position estimate, allowing the system to adapt to various operational conditions and system configurations without requiring separate processing pipelines for each sensor type.
2Reliability
If structural separation between operating and non-operating areas is implemented, then safety is improved, but adaptability decreases
Solution Approach 1:
The patent introduces a probabilistic position evaluation model as an intermediary between the positioning systems and the safety control mechanisms. This intermediary layer calculates the probability that the vehicle is within the tolerance range, providing a quantitative safety metric that enables safe operation in environments without physical barriers. The probabilistic approach acts as a virtual mediator that separates the vehicle control system from the need for physical area separation.
3Measurement precision
If centimeter-level position precision is required, then measurement precision is improved, but loss of time increases due to complex calculations
Solution Approach 1:
The patent changes the parameter of position precision from deterministic centimeter-level accuracy to probabilistic confidence levels. Instead of requiring exact position measurements, the system calculates the probability that the vehicle is within a specified tolerance range. This parameter transformation allows the use of less precise individual measurements while achieving reliable safety decisions through statistical evaluation, significantly reducing calculation complexity and time requirements.
Data Source
Figure 1
Figure 2
AI summary
In a method (V) for determining a secure position of a vehicle (1), wherein the vehicle (1) has a global navigation system (GNSS), an inertial measurement unit (IMU), and an odometry system (O), an absolute position (10) of the vehicle (1) is determined using the global navigation system (GNSS). A first relative position (11) of the vehicle (1) is determined using the inertial measurement unit (IMU). A second relative position (12) of the vehicle (1) is determined using the odometry system (O). A safety factor (20) of the absolute position (10) is determined based on an accuracy of the global navigation system (GNSS). A safety factor (21) of the first relative position (11) is determined based on an accuracy of the inertial measurement unit (IMU). A safety factor (22) of the second relative position (12) is determined based on an accuracy of the odometry system (O).The current position (13) of the vehicle (1) is determined based on its absolute position (10), first relative position (11), and second relative position (12). A certainty (23) for the current position (13) of the vehicle (1) is calculated based on the certainty (20) of the absolute position (10), the certainty (21) of the first relative position (11), and the certainty (22) of the second relative position (12). A tolerance range (25) around the current position (13) of the vehicle (1) is determined based on the certainty (20) of the absolute position (10), the certainty (21) of the first relative position (11), and the certainty (22) of the second relative position (12). A probability (26) that the vehicle (1) is located within the tolerance range (25) is determined and subsequently output.