PID Embedded LQR for Autonomous Driving Path Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Linear Quadratic Regulators (LQR) control systems for autonomous driving vehicles (ADVs) fail to effectively handle feedback errors, such as lateral drift, which can cause vehicles to deviate from predetermined paths due to wheel misalignments or other factors.
Innovation Solution
Integration of a Proportional-Integral-Derivative (PID) controller with the LQR control system to compensate for feedback errors, specifically lateral drift, by determining a second lateral distance error and generating steering commands to minimize the distance between the actual and reference paths.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If LQR control system is used for path tracking, then the vehicle can automatically steer along a predetermined path, but the system fails to adequately handle feedback errors such as lateral drift
Solution Approach 1:
The patent combines LQR control system with PID controller into a hybrid control architecture. The PID controller specifically handles feedback errors including lateral drift, while the LQR system manages overall path tracking. This merging allows the system to leverage the strengths of both controllers: LQR for optimal path following and PID for robust feedback error compensation, thereby resolving the contradiction between path tracking capability and feedback error handling.
Solution Approach 2:
The PID controller acts as an intermediary component that processes feedback errors between the sensor system and the LQR control system. It receives lateral distance errors from sensors, computes compensation values through proportional, integral, and derivative terms, and feeds these corrected error signals back to the LQR system. This intermediary role enables the LQR system to operate with improved error information, enhancing overall path tracking reliability without compromising the original LQR control architecture.
2Reliability
If PID controller is integrated with LQR system, then feedback error compensation is improved, but the device complexity increases
Solution Approach 1:
The control system is segmented into distinct functional modules: the LQR control system for optimal path tracking, the PID controller for feedback error compensation, and the sensor system for error detection. Each module performs a specific function, allowing for independent tuning and maintenance. The PID controller is further segmented into proportional, integral, and derivative components, each handling different aspects of error compensation. This segmentation reduces overall system complexity by creating manageable, specialized subsystems.
Solution Approach 2:
The hybrid control system serves multiple functions through its integrated architecture: path tracking via LQR, feedback error compensation via PID, and adaptive adjustment through the combination of both. The system can operate in different modes depending on error magnitudes and rates of change, providing universal adaptability to various driving conditions. This multi-functionality justifies the increased complexity by delivering enhanced reliability and versatility that a single-controller system cannot achieve.
Data Source
AI summary
In one embodiment, a system receives a reference trajectory including a reference path in which the ADV is to follow. The system controls the ADV along the reference path using a path tracking algorithm, including: determining a first lateral distance error, determining a second lateral distance error based on the first lateral distance error using a proportional-integral-derivative (PID) control system, where the second lateral distance error compensates for a lateral drift, and generating a steering command based on the second lateral distance error using the path tracking algorithm to control the ADV to minimize a lateral distance error, e.g., a lateral distance between an actual path taken by the ADV and the reference path.