Autonomous Vehicle Control Parameter Tuning for Changing Road Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in maintaining optimal control parameters across varying road and weather conditions, leading to uncomfortable or unsafe driving behaviors due to the use of a single set of controller parameters for all conditions, resulting in inadequately posed optimization control problems and potential oscillations in control variables.
Innovation Solution
A microcontroller unit (MCU) receives sensor data to determine the actual state of the vehicle and calculates performance metrics, adjusting weight values for the control algorithm to tune controller parameters dynamically, ensuring optimal motion planning and control by adapting to different road and weather conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single set of controller parameters is used for all driving conditions, then the device complexity is reduced, but the adaptability to different road and weather conditions deteriorates
Solution Approach 1:
The patent implements dynamic parameter adjustment by switching between different controller parameter sets based on detected road and weather conditions. The system transitions from static single-parameter control to dynamic multi-parameter control, allowing the controller to adapt its characteristics in real-time according to environmental conditions, thus resolving the contradiction between device complexity and adaptability.
Solution Approach 2:
The patent applies parameter changes by modifying controller parameters according to different operating conditions. Multiple sets of controller parameters are prepared in advance, each optimized for specific road or weather conditions. The system detects current conditions and selects the appropriate parameter set,实现ing parameter adaptation without requiring complex real-time optimization algorithms.
2Reliability
If controller parameters are tuned for specific conditions, then the motion planning performance is improved, but the device complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-tuning multiple sets of controller parameters for different road and weather conditions before actual operation. Instead of performing complex real-time parameter optimization, the system prepares optimized parameter sets in advance and simply selects the appropriate one based on detected conditions, thus improving reliability while keeping the runtime system relatively simple.
3Ease of operation
If the same control input is used under different road conditions, then the ease of operation is maintained, but the vehicle control precision deteriorates
Solution Approach 1:
The patent implements feedback by continuously monitoring road and weather conditions and using this information to select appropriate controller parameter sets. The system detects environmental conditions, compares them with predefined condition profiles, and automatically adjusts controller parameters accordingly, thus maintaining control precision without requiring manual intervention or complex real-time optimization.
Data Source
AI summary
In one embodiment, a microcontroller unit (MCU) receives an expected state of an autonomous driving vehicle (ADV) from a controller of the ADV, where the controller controls motions of the ADV using a control algorithm. The MCU receives sensor data from one or more sensors of the ADV. The MCU determine an actual state of the ADV based on the sensor data. The MCU determines a performance metric of the control algorithm based on the expected state and the actual state. In response to determining the performance metric has satisfied a predetermined condition, the MCU determines a plurality of weight values for the control algorithm. The MCU sends the plurality of weight values to the control system to tune one or more weight parameters of the control algorithm using the plurality of weight values, where the controller controls the ADV using the tuned control algorithm.