Semi-Truck Predictive Control With Linearized MPC Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving systems face challenges in accurately predicting the complex movements of semi-trucks with trailers due to additional degrees of freedom, leading to difficulties in generating precise control commands for safe and efficient navigation.
Innovation Solution
An in-vehicle control system that uses a dynamic model based on Lagrangian mechanics and quadratic programming (QP) to predict the semi-truck's response to control commands, simplifying the model into a 6-state linear system to enable efficient real-time control, incorporating a model predictive controller (MPC) and adaptive controller to generate optimized steering and throttle commands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a complex dynamic model is used to accurately predict semi-truck movements with trailers, then prediction accuracy is improved, but computational complexity and processing time increase
Solution Approach 1:
The complex dynamic model is segmented into multiple linear models, each valid within specific operating ranges. The system divides the state space into regions and selects appropriate linear models based on current operating conditions, reducing computational complexity while maintaining accuracy across different scenarios
Solution Approach 2:
The system dynamically switches between different linear models based on real-time operating conditions. A model selection mechanism continuously adapts the active model to match current vehicle state, enabling accurate predictions without requiring a single complex model to handle all scenarios
2Productivity
If a simplified linear model is used for real-time control, then processing speed is improved, but prediction accuracy deteriorates
Solution Approach 1:
The system employs dynamic model switching that adapts to real-time operating conditions. By selecting the most appropriate linear model for current operating parameters, the system maintains high prediction accuracy while utilizing computationally efficient linear models for real-time control processing
Solution Approach 2:
The system changes model parameters based on operating conditions. Different linear models have different parameter sets optimized for specific operating ranges, allowing the system to maintain accuracy across varying conditions while using simple linear computations for real-time processing
3Manufacturing precision
If multiple control commands are generated using quadratic programming, then control precision is improved, but computational time increases
Solution Approach 1:
The control problem is segmented into multiple quadratic programming subproblems, each corresponding to a specific linear model. By solving simpler QP problems for each segment rather than one complex QP problem, the system achieves comparable precision with reduced computational time
Solution Approach 2:
The system performs preliminary model selection and preparation before generating control commands. By pre-identifying the appropriate linear model and preparing relevant parameters, the system reduces the computational burden during real-time control execution
Data Source
AI summary
Systems and methods for dynamic predictive control of autonomous vehicles are disclosed. In one aspect, an in-vehicle control system for a semi-truck includes one or more control mechanisms configured to control movement of the semi-truck and a processor. The system further includes computer-readable memory in communication with the processor and having stored thereon computer-executable instructions to cause the processor to receive a desired trajectory and a vehicle status of the semi-truck, determine a dynamic model of the semi-truck based on the desired trajectory and the vehicle status, determine at least one quadratic program (QP) problem based on the dynamic model, generate at least one control command for controlling the semi-truck by solving the at least one QP problem, and provide the at least one control command to the one or more control mechanisms.