Machine Sensor Calibration Using Cross-Vehicle Reference Frames
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sensor calibration systems for machines, such as wheel loaders and haul trucks, are limited in their ability to perform calibration based on data from a single sensor and do not effectively account for the orientation and position of the sensor relative to the machine's reference frame.
Innovation Solution
A method and system that utilize observed sensor data from a separate observing machine to determine the transformation between different reference frames, allowing for the calibration of a target machine's sensor by identifying marker points and fiducial markers to establish the sensor's location and orientation within the target machine's reference frame.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor calibration is performed using data from multiple sensors on the same vehicle, then calibration between sensors can be achieved, but the system has limited ability to perform calibration based on single sensor data and body-mounted sensor data
Solution Approach 1:
The patent makes the calibration system universal by enabling it to perform calibration using multiple approaches: (1) data from multiple sensors on the same vehicle, (2) data from a single sensor, and (3) data from sensors mounted on the vehicle body. This multi-functional capability resolves the contradiction by allowing the system to adapt to different calibration scenarios while maintaining accuracy
Solution Approach 2:
The patent introduces an intermediary coordinate transformation approach that mediates between different reference frames. By establishing transformations between sensor coordinate systems and vehicle body coordinate systems, the system can calibrate sensors using various data sources (single sensor, multiple sensors, body-mounted sensors) and convert all measurements to a common reference frame, thus achieving both precision and versatility
2Measurement precision
If sensor data is captured without considering reference frame orientation and position, then data collection is simpler, but accurate interpretation of sensor data relative to the machine's reference frame cannot be achieved
Solution Approach 1:
The patent applies preliminary action by pre-defining coordinate systems and reference frames for both the sensor and the vehicle body before calibration occurs. Fiducial markers are pre-positioned on the vehicle body at known coordinates. This preliminary setup creates a structured framework that simplifies the actual calibration process, as the system only needs to determine transformations between these pre-established reference frames rather than creating them during calibration
Solution Approach 2:
The patent replaces complex mechanical alignment procedures with computational coordinate transformations. Instead of physically aligning sensors with the vehicle body using mechanical fixtures and manual measurements, the system uses mathematical transformations between coordinate systems. This substitution of mechanical processes with computational methods maintains measurement precision while reducing physical complexity
Data Source
AI summary
A target machine may have a target sensor, such as a LiDAR sensor, a radar sensor, a camera, or other sensor. The target sensor of the target machine may be calibrated based on sensor data captured by a sensor of a different observing machine, such as a LiDAR sensor on the observing machine that captures data indicative of positions of the target sensor and the target machine. The target sensor of the target machine may also or alternatively be calibrated based on sensor data captured directly by the target sensor, for instance based on location of marker points on the target machine itself that are indicated by the sensor data captured directly by the target sensor.