Unified MPC Envelope Control for Autonomous Driving Mode Transitions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems lack a unified control scheme for both semi-autonomous and fully autonomous driving modes, requiring separate hardware and control systems, which complicates transitions between modes and increases hardware requirements.
Innovation Solution
Implementing a common Model Predictive Control (MPC) envelope control scheme that uses a pseudo-driver input in fully autonomous mode, allowing for reference tracking and refinement of autonomous driving commands, thereby simplifying control and reducing hardware needs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If separate control systems are used for semi-autonomous and fully autonomous driving modes, then each mode can be optimized independently, but device complexity and hardware requirements increase
Solution Approach 1:
The patent implements a universal MPC controller that serves both semi-autonomous and fully autonomous driving modes through a single control architecture. The controller receives driving inputs from either a human driver or pseudo-driver, processes them through the same MPC framework, and generates control commands for vehicle systems, thereby eliminating the need for separate control systems while maintaining optimized performance for both modes
Solution Approach 2:
The patent merges the control logic for semi-autonomous and fully autonomous modes into a unified MPC envelope structure. By combining the reference tracking mechanisms and control algorithms into a single integrated system that handles both human driver inputs and pseudo-driver inputs, the patent reduces hardware requirements while preserving the reliability benefits of mode-specific optimization
2Reliability
If separate hardware systems are implemented for different driving modes, then mode-specific performance is optimized, but hardware requirements and system cost increase
Solution Approach 1:
The MPC controller is designed as a multi-functional system that processes both human driver inputs in semi-autonomous mode and pseudo-driver inputs in fully autonomous mode through the same hardware architecture. This universal controller eliminates the need for separate hardware systems while maintaining optimized performance characteristics for each driving mode through software-based mode differentiation
3Device complexity
If a unified control scheme is used for both driving modes, then hardware requirements are reduced and transitions are simplified, but control precision for each mode may be compromised
Solution Approach 1:
The MPC controller implements local quality by applying mode-specific reference tracking precision within the unified control framework. The system adjusts the reference input generation and tracking parameters based on the current driving mode, ensuring high precision for both semi-autonomous and fully autonomous operations while maintaining a single control hardware architecture
Solution Approach 2:
The unified MPC controller dynamically adapts its control parameters and reference tracking behavior based on the operating mode. The system transitions smoothly between semi-autonomous and fully autonomous modes by dynamically adjusting how it processes driving inputs and generates control commands, maintaining precision throughout mode transitions without requiring separate hardware systems
Data Source
AI summary
Systems and methods of using a common control scheme to autonomously control a vehicle during semi-autonomous and fully autonomous driving modes are provided. In particular, embodiments of the presently disclosed technology incorporate reference tracking for driving input and vehicle state into this common control scheme. In some embodiments, this common control scheme may be implemented using Model Predictive Control (“MPC”).