AV Sensor Calibration Path Planning During Vehicle Operation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle sensors deteriorate over time, leading to decreased performance in mapping, localization, planning, control, and perception, necessitating recalibration to maintain safety and efficiency.
Innovation Solution
An unsupervised calibration system generates calibration-aware paths along road networks that allow sensors to explore their parameter space, eliminating the need for dedicated facilities and enabling continuous updates while the vehicle is in operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vehicle sensors are recalibrated using traditional methods in dedicated facilities, then calibration accuracy is improved, but vehicle operational time is reduced and productivity decreases
Solution Approach 1:
The system enables sensors to calibrate themselves automatically by utilizing the vehicle's normal operational environment and data, eliminating the need for dedicated calibration facilities and manual intervention. The calibration process is integrated into regular vehicle operation, allowing continuous updates without removing the vehicle from service.
Solution Approach 2:
The calibration system utilizes the vehicle's existing sensor network and operational data for multiple purposes: normal sensing functions and calibration processes. The same sensors and data streams used for vehicle operation are also employed for calibration, eliminating the need for separate calibration equipment and facilities.
2Reliability
If vehicle sensors are recalibrated frequently to maintain performance, then sensor reliability is improved, but loss of time and operational delays increase
Solution Approach 1:
The calibration process occurs continuously during normal vehicle operation rather than in discrete intervals. Sensors are constantly updated using ongoing operational data, ensuring continuous improvement of calibration accuracy without interrupting vehicle service. This eliminates the start-stop nature of traditional calibration methods.
Solution Approach 2:
The system performs calibration updates in advance during normal operation, so sensors are always calibrated before critical performance is needed. By continuously updating calibration parameters during routine operation, the system ensures optimal sensor performance is maintained proactively rather than reactively.
3Measurement precision
If traditional calibration facilities are used, then calibration quality is improved, but device complexity and infrastructure requirements increase
Solution Approach 1:
The calibration function is extracted from dedicated calibration facilities and integrated into the vehicle's normal operational system. The calibration capability is embedded within the vehicle's existing sensor network and processing systems, eliminating the need for separate calibration infrastructure and reducing overall system complexity.
Solution Approach 2:
The calibration system merges the calibration function with the vehicle's normal operational sensors and data processing systems. By combining calibration activities with routine vehicle operation, the system eliminates the need for separate calibration facilities and reduces infrastructure complexity while maintaining calibration quality.
Data Source
AI summary
Among other things, techniques are described for calibrating a sensor of a vehicle. One technique involves identifying a trigger for calibrating at least one sensor of a vehicle. In response to identifying the trigger, the technique then involves initiating a calibration path planning mode for the vehicle. In the calibration path planning mode, the technique involves: generating a plurality of calibration-aware paths that each include at least one calibration trajectory along at least one road; and selecting, from the plurality of paths, a first calibration-aware path for the vehicle, where the at least one sensor is calibrated while the vehicle travels along the selected path.