Vehicle Steering Geometry Control for Real-Time Wheel Alignment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Modern vehicles face challenges in optimizing steering geometry for varying driving conditions and driver behaviors, as current systems fail to adapt dynamically to ensure optimal performance, fuel efficiency, and compliance with legal regulations.

Innovation Solution

A system utilizing reinforcement learning and neural networks to determine the current driving cycle and application of a vehicle, processing sensor data to output wheel alignment signals, which can be used to adjust steering geometry components or provide recommendations for manual adjustment, ensuring optimal alignment based on real-time data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If steering geometry is fixed for legal compliance, then vehicle can meet legal regulations, but performance and fuel efficiency cannot be optimized for varying driving conditions

Engineering Contradiction:

Improvesteering geometry adaptabilityVSAvoidsteering geometry adjustment system

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic steering geometry adjustment by enabling the steering system to change its geometric parameters (camber, toe, caster angles) in real-time based on detected driving conditions. The system transitions from a static, fixed geometry design to a dynamic one that continuously adapts to optimize performance for different driving cycles, road surfaces, and weather conditions while maintaining legal compliance.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system optimizes vehicle performance by changing key steering geometry parameters including camber angle, toe angle, and caster angle based on detected driving conditions. The machine learning model determines optimal parameter values that balance performance optimization with legal regulation compliance, allowing the steering geometry to be dynamically adjusted rather than fixed at factory settings.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If steering geometry is optimized for specific driving conditions, then fuel efficiency and performance improve, but the system cannot adapt to varying driver behavior and environmental conditions

Engineering Contradiction:

Improvefuel efficiencyVSAvoidresponse to varying conditions

Core Design Contradiction:

ProductivityVSAdaptability or versatility

Solution Approach 1:

The system employs continuous feedback loops where sensors monitor driving conditions, driver behavior patterns, and vehicle performance metrics. This feedback is processed by machine learning models that adjust steering geometry parameters in real-time to optimize fuel efficiency and performance. The feedback mechanism enables the system to learn from past driving cycles and adapt to varying conditions including different drivers, road surfaces, and weather patterns.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The steering geometry system performs self-optimization through autonomous machine learning algorithms that continuously analyze driving patterns and environmental conditions. The system automatically adjusts geometric parameters without requiring manual intervention or external calibration, enabling it to adapt to varying driver behavior and environmental conditions while maintaining optimal fuel efficiency and performance.

Inventive Principle:

Principle #25Self-service

3Manufacturing precision

If wheel alignment is manually adjusted, then steering geometry can be optimized, but the process is time-consuming and cannot respond to real-time driving conditions

Engineering Contradiction:

Improvewheel alignment precisionVSAvoidalignment adjustment time

Core Design Contradiction:

Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical wheel alignment adjustment with an automated electronic control system. Machine learning models calculate optimal steering geometry parameters and electronically control adjustment mechanisms, eliminating the need for time-consuming manual alignment processes. This substitution enables real-time adaptation to driving conditions while maintaining high alignment precision through automated control rather than human intervention.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20240017766A1System and method for reinforcement learning of steering geometry

Publication Date: 2024.01.18 VOLVO TRUCK CORP

AI summary

Systems, methods, and computer-readable storage media for adjusting the steering geometry of a vehicle by using reinforcement learning in series with a neural network to determine when and how to adjust the steering geometry of the vehicle. A system can do this by receiving vehicle information associated with ongoing movement of the vehicle, and executing a reinforcement learning model using that vehicle information. The outputs of the reinforcement learning model can include a current driving cycle of the vehicle and a current application of the vehicle. The system then executes a machine learning model, where inputs to the machine learning model can include the outputs of the reinforcement learning model and the vehicle information. The outputs of the machine learning model can then include a wheel alignment signal.