Machine Positioning via Sensor Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional machine positioning systems, such as those using GPS and LIDAR, fail to provide accurate position estimates during periods of GPS signal unavailability or unreliability due to multipath errors and position jumps, as they do not check the accuracy of GPS signals.
Innovation Solution
A system that includes a perception sensor generating scene data, a locating device receiving location signals, and a controller estimating positions based on scene data and signal accuracy, using a Kalman filter and Perception-Based Localization (PBL) to compare and validate position estimates from different sources, ensuring accurate positioning even when GPS signals are unreliable.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GPS and LIDAR data fusion is used to determine machine position, then positioning capability is provided, but accuracy deteriorates during GPS signal unavailability or when multipath errors occur
Solution Approach 1:
The system continuously compares GPS-derived position estimates with LIDAR-based position estimates and uses the discrepancy feedback to detect signal errors. When multipath errors or position jumps are detected in GPS data, the system switches to using LIDAR data, thereby maintaining measurement precision while preserving positioning reliability through continuous validation.
Solution Approach 2:
The controller acts as an intermediary that receives position data from both GPS and LIDAR systems, validates their consistency, and selects the most reliable estimate. This intermediary validation mechanism allows the system to maintain accurate position estimation even when GPS signals are unavailable or erroneous by cross-referencing with LIDAR measurements.
2Adaptability or versatility
If conventional GPS-based positioning is used, then positioning is provided, but accuracy is lost during dead-reckoning periods or when GPS signals are unreliable
Solution Approach 1:
The system dynamically changes the data source parameter based on signal reliability conditions. When GPS signals are available and reliable, the system uses GPS data; when GPS signals are unavailable or erroneous, the system switches to using LIDAR data. This parameter change strategy enables the system to adapt to varying signal conditions while maintaining measurement precision throughout.
Solution Approach 2:
The system performs preliminary validation of GPS signals against LIDAR estimates before using them for positioning. By checking for consistency and detecting errors in advance, the system can prevent the use of inaccurate GPS data and switch to alternative sources, thereby maintaining adaptability without sacrificing precision during signal degradation.
Data Source
AI summary
A system and method for estimating position of a machine is disclosed. The method may include receiving, from a perception sensor, scene data describing an environment in a vicinity of the machine and estimating a first position of the machine based on the scene data. The method may include determining whether a first signal indicative of a location of the machine is received by the machine and estimating a second position of the machine when it is determined that the first signal is received. The method may include comparing the second position with the first position and estimating a third position of the machine using at least one of the first position and the second position.