Proxy Calibration Targets for Remote Fleet Sensor Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in maintaining accurate sensor calibration, especially when ground-truth calibration targets are not readily accessible, leading to degraded calibration quality over time.
Innovation Solution
The use of candidate objects detected by recently calibrated vehicles as proxy calibration targets, allowing for remote calibration of sensors in other vehicles within a fleet by capturing and comparing data from these objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ground-truth calibration targets are used for sensor calibration, then calibration accuracy is improved, but accessibility and convenience deteriorate due to limited location availability and long travel distances
Solution Approach 1:
The patent creates virtual copies of ground-truth calibration targets by using images captured by recently calibrated vehicles. These virtual targets are stored in a database and can be accessed remotely, eliminating the need for physical presence at calibration facilities while maintaining calibration accuracy through the use of captured image data.
Solution Approach 2:
The patent introduces a remote server as an intermediary that stores and distributes virtual calibration targets. This intermediary enables vehicles to perform calibration remotely by providing access to calibration target images without requiring physical travel to calibration facilities, thus resolving the accessibility issue while maintaining accuracy.
2Measurement precision
If ground-truth calibration targets are used for sensor calibration, then calibration quality is improved, but time consumption increases due to long wait times at calibration facilities
Solution Approach 1:
By creating virtual copies of calibration targets that can be accessed remotely, the system eliminates the need for vehicles to wait in queue at physical calibration facilities. Multiple vehicles can simultaneously access the same virtual calibration targets, reducing wait time to minimal data transmission time while maintaining calibration quality.
Solution Approach 2:
The system performs preliminary calibration actions by capturing images of calibration targets with recently calibrated vehicles and storing them in advance in a database. This preliminary action allows other vehicles to immediately access pre-captured calibration data without waiting for calibration facility availability, thus reducing time loss while maintaining calibration quality.
3Measurement precision
If frequent calibration is performed to maintain sensor accuracy, then measurement precision is improved, but operational efficiency deteriorates due to reduced vehicle availability
Solution Approach 1:
The virtual calibration target system allows vehicles to perform calibration quickly by accessing pre-captured images remotely, reducing the time vehicles are taken out of service. This enables more frequent calibration without significantly impacting vehicle availability, thus maintaining sensor accuracy while preserving productivity.
Solution Approach 2:
The system enables periodic calibration at convenient intervals by allowing quick remote calibration when needed, rather than requiring lengthy calibration sessions. Vehicles can perform calibration during routine operations or at scheduled intervals without extended downtime, balancing sensor accuracy maintenance with operational efficiency.
Data Source
AI summary
Example embodiments relate to identification of proxy calibration targets for a fleet of sensors. An example method includes collecting, using a sensor coupled to a vehicle, data about one or more objects within an environment of the vehicle. The sensor has been calibrated using a ground-truth calibration target. The method also includes identifying, based on the collected data, at least one candidate object, from among the one or more objects, to be used as a proxy calibration target for other sensors coupled to vehicles within a fleet of vehicles. Further, the method includes providing, by the vehicle, data about the candidate object for use by one or more vehicles within the fleet of vehicles.