Smart Vehicle Steering Control With Parallel Risk Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current man-machine coordinated steering systems for smart vehicles face challenges in providing a real-time optimal front wheel steering angle based on risk assessment, hindering their widespread adoption due to complexities in traffic environments and driver behavior analysis.
Innovation Solution
A parallel computing method is developed to optimize front wheel steering and longitudinal acceleration by building a lateral kinetic equation model, employing a parallel computing architecture, and using fuzzy logic to compute driving weights, thereby enabling real-time control of the steering system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional sequential computing methods are used for man-machine coordinated steering control, then the control system can provide comprehensive risk assessment and optimal steering angle calculation, but the computing time is too long to achieve real-time control
Solution Approach 1:
The patent divides the control system into multiple independent computing modules: risk assessment module, prediction model module, target function module, and optimization module. Each module processes specific tasks independently through parallel computing, thereby reducing overall computing time while maintaining comprehensive control accuracy.
Solution Approach 2:
The patent transitions from sequential single-thread computing to parallel multi-thread computing architecture, adding a temporal dimension to the processing. Multiple computations that were previously executed one after another are now executed simultaneously across multiple processing units, dramatically reducing computing time.
2Productivity
If real-time parallel computing is implemented for optimal steering angle calculation, then the computing speed is improved, but the system complexity increases
Solution Approach 1:
The control system is segmented into functionally independent modules that can be developed, tested, and maintained separately. This modular architecture reduces system complexity by organizing complex parallel computing tasks into manageable units with well-defined interfaces.
Solution Approach 2:
The patent introduces a coordinate transformation module as an intermediary between the prediction model and the optimization module. This intermediary handles the complex data format conversions and coordinate system transformations, isolating the complexity from the core parallel computing algorithms and simplifying the overall system architecture.
3Reliability
If comprehensive risk assessment and prediction models are used for safe driving control, then the driving safety is improved, but the computational burden increases and real-time performance deteriorates
Solution Approach 1:
The patent extracts only the essential and most critical risk factors from comprehensive environmental data, such as key obstacle positions, relative velocities, and critical distance metrics. By focusing computational resources on these extracted critical parameters rather than processing all available sensor data, the system maintains high driving safety while reducing computational burden.
Solution Approach 2:
The patent dynamically adjusts the complexity and detail level of risk assessment parameters based on driving conditions. In normal driving conditions, simplified parameter models are used to reduce computational burden, while in critical situations, more comprehensive parameter analysis is activated to ensure safety, thereby optimizing the balance between safety and computational efficiency.
Data Source
AI summary
A parallel computing method for man-machine coordinated steering control of a smart vehicle based on risk assessment is provided, comprising the following steps: building a lateral kinetic equation model of a vehicle; building a target function by targeting at minimizing an offset distance of a vehicle driving track from a lane center line and making a change in a front wheel steering angle and a longitudinal acceleration as small as possible in a driving process; building a parallel computing architecture of a prediction model and the target function, and employing a triggering parallel computing method; solving and computing a gradient with a manner of back propagation and using a gradient descent method to obtain an optimal control amount of the front wheel steering angle and an optimal control amount of the longitudinal acceleration; and computing a driving weight, obtaining a desired front wheel steering angle and completing real time control.