Collaborative Sensor Calibration Using Route Landmarks in Truck Fleets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving technologies do not adequately address the unique challenges faced by trucks and truck fleets, such as the need for accurate and reliable sensor calibration while in motion, and the dynamic monitoring of trailer positions to ensure safe lane adherence.
Innovation Solution
A system and method for collaborative sensor calibration on-the-fly using landmarks or other fleet members, involving a fleet management center to coordinate sensor calibration assistance, utilizing visual targets with known features to recalibrate sensors while vehicles are in motion, and employing fiducial markers for trailer pose estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor calibration is performed using traditional methods requiring the vehicle to stop, then calibration accuracy is improved, but vehicle productivity and operational efficiency deteriorate due to downtime
Solution Approach 1:
The patent enables sensor calibration to be performed dynamically while the vehicle is in motion, rather than requiring the vehicle to stop. The system captures images of calibration targets from multiple moving vehicles, processes these images to determine sensor calibration parameters, and applies corrections without interrupting vehicle operations. This dynamic calibration approach maintains calibration accuracy while preserving vehicle productivity.
Solution Approach 2:
The calibration system uses the vehicles themselves and their existing sensors to perform the calibration process. Multiple vehicles in the fleet capture images of calibration targets, and the system processes these self-collected data to determine calibration parameters. This self-service approach eliminates the need for external calibration equipment and vehicle downtime, thereby maintaining both accuracy and productivity.
2Reliability
If collaborative calibration using multiple fleet members is implemented, then calibration reliability is improved, but system complexity increases due to coordination requirements
Solution Approach 1:
The calibration system is integrated into the existing fleet management infrastructure, using the same communication networks, processors, and control systems that vehicles already employ for their primary operations. The calibration coordination functions are performed by existing fleet management software and hardware, eliminating the need for separate dedicated calibration coordination systems and reducing overall complexity.
Solution Approach 2:
The patent introduces a calibration coordination module that acts as an intermediary between vehicles and the calibration process. This module receives calibration requests from vehicles, identifies suitable calibration targets and assisting vehicles, coordinates the calibration process, and processes calibration data. By centralizing coordination functions in a dedicated intermediary component, the system manages complexity while improving calibration reliability through coordinated multi-vehicle participation.
3Measurement precision
If fiducial markers are used for trailer pose estimation, then measurement precision is improved, but device complexity increases due to additional monitoring systems
Solution Approach 1:
The system uses the same cameras and image processing algorithms that vehicles employ for primary autonomous driving functions to detect and track fiducial markers on trailers. The existing sensor suites and processing systems serve dual purposes: navigation and trailer monitoring. This multi-functionality approach improves measurement precision for trailer pose estimation without requiring separate dedicated monitoring hardware, thereby avoiding increased device complexity.
Data Source
AI summary
The present teaching relates to method, system, medium, and implementations for sensor calibration. An ego vehicle determines whether a sensor deployed thereon to facilitate autonomous driving needs to be calibrated and sends, if it is determined that the sensor needs to be calibrated, a request for assistance in collaborative calibration of the sensor to a center. The request includes at least a first position of the ego vehicle on the route and a first configuration of the sensor with respect to the ego vehicle. When the ego vehicle receives a calibration assistant package, which includes information associated with a collaborative means present along the route and to be used to assist the ego vehicle to calibrate the sensor, it identifies, based on the information, the collaborative means along the route when the ego vehicle is in a vicinity of the collaborative means in order to capture a target present on the collaborative means to enable calibration of the sensor.