Probabilistic Tire Slip Control Under Changing Road Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately control longitudinal tire slip and force for vehicles operating on varying road conditions, such as wet mud, gravel, sand, and snow, as the relationship between tire force and slip is not well understood, making it difficult to achieve maximum traction and manage lateral forces effectively.
Innovation Solution
A computer system using a non-parametric probabilistic model, like Gaussian process regression, to predict tire force based on slip and provide confidence intervals, allowing for adaptive slip control that can handle changing conditions and uncertainty.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed longitudinal slip value (e.g., 10%) is used to achieve maximum traction, then the control system is simple to implement, but the system cannot adapt to different road conditions (asphalt, mud, gravel, sand, snow, ice) where peak slip varies from 7% to 30%
Solution Approach 1:
The system performs self-learning by automatically collecting slip and force data during vehicle operation, building probabilistic models without external intervention. The vehicle's own operational data is used to train the model, enabling the system to adapt to different road conditions autonomously
Solution Approach 2:
The system continuously collects feedback from sensors measuring longitudinal slip and tire force during vehicle operation. This feedback is used to update and refine the probabilistic model, allowing the system to learn and adapt to changing road conditions in real-time
2Force
If maximum longitudinal tire force is always pursued, then traction is optimized, but lateral tire force generation is reduced and vehicle stability is compromised
Solution Approach 1:
Instead of always operating at peak longitudinal force, the system uses the probabilistic model to determine appropriate levels of longitudinal slip and force based on current driving conditions and requirements. This allows operating at or near peak when needed while maintaining safety margins when lateral stability is prioritized
Solution Approach 2:
The system dynamically adjusts the target longitudinal slip value based on real-time conditions and vehicle state. The probabilistic model provides a distribution of possible peak slip values, allowing the controller to select appropriate operating points that balance longitudinal traction with lateral stability requirements
3Reliability
If traditional deterministic models are used to predict tire force-slip characteristics, then the model structure is simple, but the system cannot provide uncertainty quantification and confidence intervals needed for safe control
Solution Approach 1:
The patent replaces traditional deterministic mathematical models with data-driven probabilistic models (such as Gaussian process regression). This substitution allows the system to capture the complex, non-linear relationship between slip and force while providing natural uncertainty quantification through the probabilistic framework
Solution Approach 2:
The system transitions from fixed-parameter deterministic models to probabilistic models with distributed parameters. The probabilistic approach provides not just a single predicted force value but a distribution characterized by mean and variance, enabling uncertainty-aware control decisions
Data Source
AI summary
A computer system is provided, including processing circuitry configured to use a non-parametric probabilistic model to obtain a prediction of how longitudinal tire force depends on longitudinal slip and one or more confidence intervals for the prediction, based on observations indicative of longitudinal slip and longitudinal tire force of a vehicle or machine. The processing circuitry is further configured to control a longitudinal slip of a vehicle or machine based on the prediction and the one or more confidence intervals. A corresponding vehicle or machine, computer program product and computer-readable storage medium are also provided.