Autonomous Vehicle Control Parameter Calibration via Offset Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle control parameter calibration in autonomous driving is typically manual and offline, which can lead to inaccuracies and inefficiencies, particularly in dynamic driving conditions.
Innovation Solution
A method and apparatus for autonomously calibrating vehicle control parameters by determining a current offset data reference value and performing offset correction based on the difference between current and historical data, allowing for real-time adjustments to ensure accurate vehicle trajectory following.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual offline calibration is used for vehicle control parameters, then the calibration process is simple to implement, but the calibration accuracy and adaptability to dynamic driving conditions deteriorate
Solution Approach 1:
The system performs self-calibration by automatically collecting offset data during vehicle operation, determining reference values, and correcting control parameters without manual intervention. The vehicle controller autonomously executes the calibration process using sensors and processors already present in the system, transforming manual calibration into an automated self-service operation that maintains accuracy while reducing complexity.
Solution Approach 2:
The calibration system continuously monitors vehicle operation data, compares actual control indicator values with expected values, and uses the offset information to automatically adjust control parameters. This feedback loop ensures calibration accuracy adapts to dynamic driving conditions while the automated process maintains implementation simplicity.
2Device complexity
If manual offline calibration is used for vehicle control parameters, then the system complexity is low, but the adaptability to dynamic driving conditions deteriorates
Solution Approach 1:
The calibration system transitions from static offline calibration to dynamic online calibration by continuously updating control parameters based on real-time vehicle operation data. The system adapts to changing driving conditions by collecting offset data during actual vehicle operation and adjusting parameters dynamically, maintaining low complexity through automated processes while significantly improving adaptability.
Solution Approach 2:
The vehicle controller autonomously performs calibration adjustments based on sensed vehicle parameters and control indicator performance, enabling the system to adapt to dynamic conditions without increasing operational complexity. The self-service mechanism automatically handles parameter adjustments in response to changing driving environments.
3Measurement precision
If frequent calibration is performed to improve accuracy, then calibration precision improves, but the calibration time and processing overhead increase
Solution Approach 1:
The system performs calibration at periodic intervals based on vehicle operation duration or mileage, rather than continuously or manually. This periodic calibration approach maintains precision by regularly updating parameters while minimizing time loss by avoiding excessive calibration frequency. The controller automatically determines when calibration is needed based on preset conditions.
Solution Approach 2:
The automated calibration system performs corrections in the background during normal vehicle operation without requiring dedicated calibration time or interrupting driving. The self-service mechanism efficiently processes calibration data and updates parameters with minimal impact on vehicle usage, balancing precision requirements with time efficiency.
Data Source
AI summary
Embodiments of the disclosure disclose a method and an apparatus for calibrating a vehicle control parameter, an on-board controller, and an autonomous vehicle; one embodiment of the method comprises: executing a calibrating step in response to reaching a preset update condition, the calibrating step comprises: obtaining a current offset data set, wherein the current offset data in the current offset data set are determined in a period of time including a current time point; determining a current offset data reference value for characterizing a value feature of the current offset data set; and performing offset correction for the vehicle control parameter based on an offset between the current offset data reference value and a historical offset data reference value. This embodiment implements autonomous calibration of the vehicle parameter based on changes of vehicle offset, such that the vehicle may accurately follow a corresponding control indicator.