Autonomous Vehicle Navigation System for Hydroplaning Risk Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation systems for autonomous vehicles are reactive and fail to predict loss of traction events, such as hydroplaning, effectively, leading to potential hazards and unsafe driving conditions.
Innovation Solution
A method and system that utilize real-time roadway data and historical geographical data to generate lane-level risk assessments, allowing for the creation of virtual lanes to avoid hazardous areas, thereby preventing loss of traction events by providing proactive routing instructions to vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If reactive detection systems (tire-mounted sensors, surround-view cameras) are used to identify hydroplaning events, then detection capability is provided, but the system cannot predict loss of traction events before they occur
Solution Approach 1:
The system performs preliminary actions by collecting and analyzing weather data, road condition data, and vehicle performance data before loss of traction events occur. This enables the system to predict hazardous conditions in advance, allowing proactive routing decisions rather than reactive responses after hydroplaning begins.
Solution Approach 2:
The system introduces an intermediary predictive layer between the environmental conditions and the vehicle control system. By using machine learning models that process weather, road, and vehicle data, the system mediates between raw environmental factors and actionable predictions, enabling early warning before actual loss of traction occurs.
2Adaptability or versatility
If handover control to human driver is implemented when hydroplaning conditions are detected, then human judgment is utilized, but the vehicle may be veering out-of-control and the operator may not have sufficient time to respond
Solution Approach 1:
The system performs preliminary routing adjustments before the vehicle enters hazardous conditions. By predicting loss of traction events in advance, the system proactively modifies the route or provides advance warning to the driver, ensuring sufficient response time rather than attempting emergency handover when the vehicle is already out of control.
Solution Approach 2:
The system applies preliminary anti-action by taking preventive measures before the harmful effect occurs. Instead of reacting to hydroplaning after it starts, the system predicts hazardous conditions and adjusts routing or alerts the driver in advance, preventing the dangerous situation from developing.
3Ease of operation
If existing navigation systems provide routing instructions, then basic navigation is provided, but the systems cannot predict or avoid loss of traction events
Solution Approach 1:
The navigation system performs preliminary risk assessments by analyzing weather data, road condition data, and predictive models before generating routing instructions. This enables the system to identify and avoid segments with high probability of loss of traction events, providing safe routing in advance rather than basic navigation after hazards occur.
Solution Approach 2:
The system incorporates feedback loops where vehicle performance data, weather updates, and road condition information continuously refine the predictive models. This feedback mechanism allows the navigation system to adapt routing recommendations based on real-time conditions and predicted changes, improving safety while maintaining ease of operation.
Data Source
AI summary
System and methods are provided for predicting, reacting to, and avoiding loss of traction events, such as hydroplaning for autonomous vehicles. For example, the method predicts a risk of an area being subject to hydroplaning using real-time data and/or historical data. The method may store possible hydroplaning events in a geographic map along with a risk assessment. The method provides lane level hydroplaning risk predictions and avoidance mechanisms.