Vehicle Dynamic Model Updating for Lateral Control Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems face challenges in maintaining control accuracy due to changes in vehicle weight and mass center position, particularly during loading and unloading conditions, which affect dynamic parameters and impact lateral control accuracy in autonomous driving scenarios.
Innovation Solution
A method and apparatus for determining vehicle control parameters by obtaining a lateral offset sequence and control input sequence, training a pre-established vehicle dynamic model, and resolving the mass and mass distribution of the vehicle from the trained model to update control parameters autonomously, thereby reducing the adverse impact on control accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If fixed vehicle dynamic parameters are used, then device complexity is reduced, but control accuracy deteriorates when vehicle weight or mass center position changes
Solution Approach 1:
The patent implements dynamic updating of vehicle control parameters by training a vehicle dynamic model with real-time lateral offset sequences and control input sequences. The model automatically adapts to changes in vehicle weight and mass center position during operation, transforming the static parameter system into a dynamic one that maintains control accuracy under varying loading conditions
Solution Approach 2:
The patent changes the parameters of the vehicle dynamic model through automated training processes. By inputting lateral offset sequences and control input sequences, the system updates the vehicle mass and mass distribution parameters without manual intervention, allowing the control system to adapt to different loading conditions while maintaining simplicity
2Manufacturing precision
If manual updates of vehicle control parameters are implemented, then control accuracy is improved, but ease of operation deteriorates due to required manual calibration
Solution Approach 1:
The patent enables the vehicle control system to automatically update its own parameters through self-service. The vehicle dynamic model is trained using real-time operational data (lateral offset sequences and control input sequences), allowing the system to autonomously adapt to changes in vehicle conditions without requiring manual calibration or external intervention
3Manufacturing precision
If frequent training of vehicle dynamic model is performed, then control accuracy is improved, but use of energy increases due to computational requirements
Solution Approach 1:
The patent implements periodic training of the vehicle dynamic model at predetermined time intervals rather than continuously. This approach balances the need for accurate parameter determination with energy consumption constraints, allowing the system to maintain control accuracy while avoiding excessive computational energy usage by training the model at appropriate intervals during vehicle operation
Data Source
AI summary
Embodiments of the present disclosure disclose a method for determining a vehicle control parameter, an apparatus for the same, a vehicle on-board controller, and an autonomous vehicle. An embodiment of the method comprises: obtaining a lateral offset sequence of a vehicle and a control input sequence of a controller for controlling a lateral output of the vehicle, wherein a lateral offset in the lateral offset sequence is for characterizing an offset between an actual lateral output of the vehicle and a desired lateral output; executing a step of determining a vehicle control parameter; wherein the executing the step of determining the vehicle control parameter includes: with the lateral offset sequence as an input and the control input sequence as the desired output, training a pre-established vehicle dynamic model to obtain a trained vehicle dynamic model; and determining the vehicle control parameter from the trained vehicle dynamic model.