Moving Vehicle Sensor Calibration Using Fleet Assistance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving technologies do not adequately address the unique challenges of sensor calibration and truck/trailer configuration awareness, leading to inaccurate obstacle avoidance and lane control in trucks and truck fleets, particularly during motion.
Innovation Solution
A system and method for collaborative sensor calibration, where moving vehicles within a fleet assist each other in recalibrating sensors on-the-fly using communication platforms and landmarks with known features, and fiducial marker-based estimation to monitor and adjust truck/trailer configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sensor calibration methods are used for autonomous trucks, then calibration can be performed in controlled environments, but the system cannot perform on-the-fly calibration during motion which leads to outdated sensor data
Solution Approach 1:
The patent transforms static calibration (performed when vehicle is stationary in controlled environments) into dynamic calibration (performed during vehicle motion). The system enables sensors to be calibrated while the autonomous truck is moving by using other vehicles in the fleet as moving calibration targets, thereby maintaining measurement precision without requiring the vehicle to stop or return to controlled environments.
Solution Approach 2:
The patent implements a self-service calibration mechanism where the autonomous truck performs its own calibration using resources from its environment (other fleet vehicles). The ego vehicle receives calibration assistance requests from other vehicles and uses its sensors to capture images of calibration targets on assisting vehicles, eliminating the need for external calibration facilities or manual intervention.
2Measurement precision
If autonomous trucks operate in fleets with close formations, then collaborative calibration can be performed, but the risk of collision between vehicles increases
Solution Approach 1:
The patent incorporates a feedback mechanism where the system continuously monitors the relative positions and distances between the ego vehicle and assisting vehicles during calibration. The calibration assistance request includes position information, and the system adjusts the calibration process based on real-time spatial feedback to maintain safe distances while achieving accurate calibration.
Solution Approach 2:
The patent changes the spatial parameters of the calibration process by allowing flexible positioning of assisting vehicles at various distances and angles relative to the ego vehicle. Instead of requiring fixed close formations, the system can perform calibration with vehicles at different relative positions, thereby maintaining calibration accuracy while reducing collision risk through parameter optimization.
3Loss of time
If trucks maintain large geographical coverage awareness, then they can plan actions in advance, but the system complexity for monitoring and adjusting truck/trailer configurations increases
Solution Approach 1:
The patent segments the configuration monitoring task by dividing it into modular components: individual sensor units (cameras, LiDAR, radar) each responsible for specific detection functions, and a centralized processing system that integrates data from these segments. This segmentation allows the system to maintain large geographical coverage awareness through distributed sensing while reducing overall complexity through functional decomposition.
Solution Approach 2:
The patent implements multi-functional sensors that can perform both autonomous driving perception tasks and calibration functions simultaneously. The same camera array used for obstacle detection also captures images of calibration targets on assisting vehicles, eliminating the need for separate dedicated calibration hardware and reducing system complexity while maintaining comprehensive awareness capabilities.
Data Source
AI summary
Embodiments described herein include a method of receiving, by a moving assisting vehicle, a calibration assistance request related to a moving ego vehicle that requested assistance in collaborative calibration of a sensor deployed on the moving ego vehicle. The method further includes analyzing the calibration assistance request to extract at least one of a schedule or an assistance route associated with the requested assistance. The method includes communicating with the moving ego vehicle about a desired location relative to the position of the moving ego vehicle for the moving assisting vehicle to be in order to assist the sensor to acquire information of a target present on the moving assisting vehicle. The method includes facilitating to drive the moving assisting vehicle to reach the desired location to achieve the collaborative calibration of the sensor on the moving ego vehicle.