Vehicle Control Device Stopping Error Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control technologies face challenges in accurately stopping vehicles at predetermined positions due to difficulties in sensing road surface conditions and individual brake differences, leading to potential large stopping errors, especially under varying conditions like sunny or rainy days, and are affected by communication delays and noise.
Innovation Solution
A vehicle control device that uses machine learning to calculate a model formula representing the relationship between the predetermined and actual stopping positions, predicts stopping errors, and updates running-condition parameters with correction values to correct stopping errors, ensuring accurate automatic stop control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If machine learning is used to calculate model formula representing stopping position relationships, then stopping accuracy is improved, but device complexity increases
Solution Approach 1:
The system implements feedback by calculating stopping errors from actual stopping positions, inputting these errors into a machine learning model to generate correction values, and applying corrections to running-condition parameters. This closed-loop feedback mechanism continuously improves stopping accuracy while managing system complexity through iterative learning rather than complex hardware modifications.
Solution Approach 2:
The control device performs self-learning and self-correction by using its own stopping error data to train the machine learning model and automatically adjust running-condition parameters. This self-service approach eliminates the need for external calibration equipment or manual adjustments, improving stopping accuracy without proportionally increasing device complexity.
2Manufacturing precision
If correction values are applied to running-condition parameters, then stopping error is reduced, but control precision requirements increase
Solution Approach 1:
The system changes parameters by applying correction values to running-condition parameters based on machine learning predictions. Instead of requiring ultra-precise measurement of individual parameters, the system uses statistical correction values that account for cumulative errors, thereby reducing stopping error without imposing extreme precision requirements on individual parameter measurements.
Solution Approach 2:
The machine learning model acts as an intermediary between raw sensor data and control commands. It processes stopping errors and generates correction values that mediate between measurement uncertainties and final control actions, reducing the impact of measurement precision limitations while achieving improved stopping accuracy.
3Adaptability or versatility
If machine learning model is updated continuously, then adaptability to different conditions is improved, but processing time increases
Solution Approach 1:
The system performs preliminary actions by pre-calculating correction values using the machine learning model before actual stopping maneuvers. The model is trained offline on historical data, and during operation, it quickly applies pre-computed corrections based on current conditions. This preliminary preparation enables rapid adaptation to different conditions without excessive processing time during critical stopping phases.
Solution Approach 2:
The system implements periodic action by updating the machine learning model at scheduled intervals or after accumulating sufficient training data, rather than continuously during operation. This periodic updating maintains adaptability to changing conditions while minimizing processing time requirements during normal operation, balancing versatility with efficiency.
Data Source
AI summary
A model formula representing the relationship between an error between a predetermined stopping position and an actually-stopped position of a vehicle indicating the result of an automatic stop control, which controls the vehicle to stop at the predetermined stopping position using running-condition parameters, and the running-condition parameters used for the automatic stop control is calculated via machine learning. A stopping error is estimated with respect to the next stopping position, at which the vehicle currently running is going to stop, according to the model formula which is calculated in the past. The changing parameter to be changed is specified among the running-condition parameters, and then the changing parameter used for the automatic stop control is updated with a correction value configured to correct the stopping error of the vehicle.