Autonomous Vehicle Control Error Detection and Parameter Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle control systems do not account for physical changes and wear in vehicles, such as tire wear and brake wear, which can affect navigation, safety, and passenger comfort, leading to suboptimal performance over time.
Innovation Solution
A computer-implemented method for an autonomous driving vehicle that monitors and adjusts control inputs based on real-time state data compared to stored data, using a state database to determine changes in vehicle performance and adjust parameters such as throttle, braking, and steering, and a server system that uses machine learning to analyze crowd-source data to update control input parameters and recommend maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicle control systems use fixed control inputs based on initial vehicle conditions, then the system complexity remains low, but the navigation accuracy and safety deteriorate over time due to vehicle wear and aging
Solution Approach 1:
The control system transitions from static fixed control inputs to dynamic adaptive control inputs that automatically adjust based on real-time vehicle state monitoring and wear detection, allowing the system to maintain navigation accuracy while adapting to changing vehicle conditions
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring vehicle state data, comparing actual performance against expected performance, and automatically adjusting control inputs based on detected deviations caused by wear and aging components
2Measurement precision
If the control system continuously monitors and adjusts control inputs in real-time, then the navigation accuracy and safety improve, but the computational load and system complexity increase
Solution Approach 1:
The system applies partial monitoring and adjustment by focusing computational resources on detecting specific wear patterns and adjusting only the control inputs that are most affected by vehicle degradation, rather than continuously optimizing all control parameters
Solution Approach 2:
The system performs preliminary analysis by establishing baseline vehicle performance characteristics and predicted wear patterns, allowing it to anticipate required control adjustments before actual performance degradation occurs, reducing real-time computational demands
3Productivity
If the system adapts control inputs to compensate for vehicle wear, then the productivity and safety improve, but the difficulty of detecting and measuring wear conditions increases
Solution Approach 1:
The system uses intermediary indicators such as deviations in actual versus expected vehicle state, abnormal sensor readings, and performance metrics that indirectly reveal wear conditions, making it easier to detect and measure wear without requiring direct sensors for each component
Solution Approach 2:
The system replaces direct mechanical wear sensors with data-driven detection methods that use patterns in vehicle operation data, control input effectiveness, and state measurements to infer wear conditions through machine learning and statistical analysis
Data Source
AI summary
State of an autonomous driving vehicle (ADV) is measured and stored for a location and speed of the ADV. Later, the state of the ADV is measured for the location and speed corresponding to a previously stored state of the ADV at the same location and speed. Fields of the measured stored states of the ADV are compared. If one or more differences between the measured and stored ADV states exceeds a threshold, then one or more control input parameters of the ADV is adjusted, such as steering, braking, or throttle. Differences may be attributable to road conditions or to state of servicing of the ADV. Differences between measured and stored states of the ADV can be passed to a service module. Service module can access crowd sourced data to determine whether one or more control input parameters for a driving state of one or more ADVs should be updated.