Vehicle Control State Machines for Modular Intelligent Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing intelligent driving technologies suffer from low algorithm update and development efficiency due to high coupling among algorithms for different application scenarios, requiring simultaneous updates across multiple sensors.
Innovation Solution
Decouple algorithms for intelligent driving functions into multiple function modules, partitioning them into task flows, allowing independent development and update of individual modules without affecting other scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If algorithms for intelligent driving functions are coupled together to handle multiple sensors and scenarios, then the system can achieve comprehensive intelligent driving functionality, but the coupling degree among algorithms increases, resulting in low development and update efficiency
Solution Approach 1:
The patent segments the coupled algorithm system into independent function modules, each responsible for specific sensor processing or driving functions. This modular architecture allows algorithms to be divided and managed separately, reducing coupling while maintaining comprehensive functionality through module composition.
Solution Approach 2:
The patent creates a universal function module framework where each module can serve multiple intelligent driving scenarios. The modules are designed with standardized interfaces and state machine mechanisms that enable them to be reused across different applications, achieving versatility without requiring tight coupling of scenario-specific algorithms.
2Reliability
If all algorithms using a certain sensor's data are updated together, then data consistency is maintained, but the update efficiency and development speed decrease
Solution Approach 1:
The patent segments the algorithm update process by assigning each sensor processing function to an independent module. This allows selective updating of individual modules without requiring system-wide updates, thereby improving update efficiency while maintaining data consistency through the module interface contracts.
Solution Approach 2:
The patent uses state machine parameters and configuration files to control module execution and updates. By changing parameters such as module activation states, execution priorities, and configuration settings, the system can update individual modules dynamically without affecting other parts, balancing consistency and efficiency.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
The present application provides a method and apparatus for controlling a vehicle, a device, and a readable storage medium. The vehicle currently executes a target intelligent driving function to perform intelligent driving. The method includes: acquiring a state of a target state machine corresponding to the target intelligent driving function and chassis data, where the target state machine is a driving state machine or a parking state machine; acquiring a state of an algorithm state machine of at least one function module corresponding to the target intelligent driving function according to the state of the target state machine and the chassis data, where the state of the algorithm state machine is used to represent a state of the function module; determining a task flow to be executed by the function module according to the state of the algorithm state machine; executing the task flow to acquire an execution result of the task flow; performing intelligent driving according to the execution result of the task flow. The present application may achieve a reduced coupling degree among algorithms for intelligent driving functions.