Autonomous Vehicle Torque Feedback Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual calibration methods for autonomous driving vehicles are not scalable, making it difficult to maintain accurate longitudinal control in autonomous driving systems.
Innovation Solution
A computer-implemented method for updating a calibration table in autonomous driving vehicles by determining torque values before and after executing control commands, calculating torque errors, and adjusting the calibration table entries based on these errors to improve control operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual calibration methods are used for autonomous driving vehicles, then calibration can be performed with simple equipment, but the method is not scalable and requires significant time for each vehicle
Solution Approach 1:
The calibration system performs self-calibration by automatically determining torque values, calculating torque errors, and updating calibration table entries without requiring manual intervention. The processor autonomously executes the calibration algorithm using sensor data from the vehicle platform, enabling the system to calibrate itself and eliminating the need for manual calibration procedures.
Solution Approach 2:
The system performs preliminary calibration actions by pre-determining torque values at different operating points and storing them in a calibration table before actual operation. This pre-calibration data is then used during autonomous driving to quickly adjust control commands without requiring time-consuming manual calibration during deployment.
2Measurement precision
If manual calibration is performed for each vehicle, then individual vehicle characteristics can be addressed, but the process requires excessive time and human resources
Solution Approach 1:
The calibration system continuously monitors actual vehicle torque output and compares it with expected torque values from the calibration table. Based on the torque error feedback, the system automatically updates the calibration table entries to minimize the difference between actual and expected torque, thereby improving calibration accuracy through iterative feedback loops.
Solution Approach 2:
The system dynamically adjusts calibration parameters by changing the torque values in the calibration table based on measured torque errors. This parameter adaptation allows the system to optimize calibration accuracy for each vehicle's specific characteristics while performing the calibration automatically during normal operation rather than requiring separate manual calibration sessions.
3Ease of operation
If a fixed calibration table is used, then control commands are simple to execute, but the system cannot adapt to variations in vehicle performance
Solution Approach 1:
The calibration table is transformed from a static fixed set of values to a dynamic structure that automatically updates during vehicle operation. The processor continuously adjusts the torque values in the calibration table based on real-time torque measurements and calculated errors, enabling the system to adapt to vehicle performance variations while maintaining simple table-lookup control execution.
Solution Approach 2:
The control system performs self-calibration by automatically updating its own calibration table using feedback from torque sensors and performance measurements. This self-adjusting capability allows the system to maintain optimal control accuracy across different operating conditions and vehicle variations without requiring external recalibration intervention.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
A computer-implemented method for operating an autonomous driving vehicle (ADV) is disclosed, the method comprising: determining a first torque value at a first time instant prior to executing a control command; determining a control command based on a speed of the ADV, a desired acceleration, and an associated entry in a calibration table; executing the control command; determining a second torque value at a second time instant subsequent to executing the control command; determining a torque error value as a difference between the first and second torque values; updating the associated entry in the calibration table based at least in part on the torque error value; and generating driving signals based at least in part on the updated calibration table to control operations of the ADV. A non-transitory machine-readable medium and a data processing system are also disclosed.