Autonomous Vehicle Speed Control Auto-Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional motion planning and control systems for autonomous driving vehicles do not efficiently account for differences in vehicle types and load variations, leading to inaccuracies in velocity calibration, which requires cumbersome manual recalibration and is not adaptive to changing conditions.
Innovation Solution
A computer-implemented method that receives control commands and speed measurements, determines expected acceleration, calculates feedback errors, and updates a calibration table in real-time to generate autonomous control commands, allowing for adaptive speed control adjustments based on current vehicle conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional motion planning and control systems are used without considering vehicle type and load differences, then the system complexity is reduced and ease of operation is improved, but manufacturing precision and measurement precision of velocity calibration deteriorate
Solution Approach 1:
The system dynamically adjusts velocity calibration parameters based on detected vehicle type and load conditions. The calibration table stores multiple velocity values corresponding to different vehicle types and load levels, and the system automatically selects and applies the appropriate calibration parameters, thereby maintaining high measurement precision without increasing operational complexity
Solution Approach 2:
The system performs automatic velocity calibration by detecting vehicle type and load characteristics, then self-adjusts the calibration parameters without requiring manual intervention. This self-calibration mechanism eliminates the need for operators to manually adjust settings for different vehicle configurations, maintaining ease of operation while ensuring accurate velocity measurement
2Measurement precision
If manual recalibration is performed for different vehicle types and load conditions, then velocity calibration precision is improved, but loss of time and productivity deteriorate
Solution Approach 1:
The system pre-establishes a calibration table containing velocity calibration parameters for multiple vehicle types and load conditions before operation. When the vehicle operates, the system automatically detects the current vehicle type and load level, then quickly retrieves and applies the corresponding pre-calculated calibration parameters, eliminating the need for time-consuming manual recalibration while maintaining high velocity measurement precision
Solution Approach 2:
The system performs automatic self-calibration by detecting vehicle type and load characteristics, then automatically adjusts calibration parameters without requiring manual intervention. This self-calibration mechanism eliminates the time loss associated with manual recalibration operations while ensuring accurate velocity calibration for different vehicle configurations
3Device complexity
If the same motion planning and control is applied to different vehicle types and load conditions, then device complexity is reduced, but adaptability deteriorates
Solution Approach 1:
The system maintains a unified motion planning and control framework but dynamically adjusts velocity calibration parameters based on detected vehicle type and load conditions. The calibration table stores multiple velocity values corresponding to different vehicle types and load levels, allowing the system to adapt to various vehicle configurations without increasing overall device complexity
Solution Approach 2:
The system employs a universal motion planning and control architecture that can handle different vehicle types and load conditions through a single integrated system. By incorporating a calibration table that accommodates multiple vehicle configurations and using automatic detection mechanisms, the system achieves multi-functionality and adaptability without requiring separate control systems for each vehicle type
Data Source
AI summary
According to some embodiments, a system receives a first control command and a speed measurement of the ADV. The system determines an expected acceleration of the ADV based on the speed measurement and the first control command. The system receives an acceleration measurement of the ADV. The system determines a feedback error based on the acceleration measurement and the expected acceleration. The system updates a portion of the calibration table based on the determined feedback error. The system generates a second control command to control the ADV based on the calibration table having the updated portion to control the ADV autonomously according to the second control command.


