Autonomous Vehicle Control Using Network Driving Condition Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle control systems lack the ability to identify and adapt to optimal driving conditions based on real-time data from a network of vehicles, leading to potential safety issues such as tailgating and inadequate responses to road conditions.
Innovation Solution
A system utilizing big data and imaging techniques to create a safer driving network by generating comprehensive profiles of autonomous vehicles, applying machine learning to identify trends and optimal driving conditions, and controlling vehicle subsystems through cloud computing, including adjustments for safe distances and speed based on vehicle profiles and road conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If autonomous vehicle control systems use basic velocity control based on preceding vehicle velocity, then the control system is simple to implement, but the system cannot identify optimal driving conditions or adapt to different driving scenarios
Solution Approach 1:
The patent introduces cloud computing services as an intermediary between the vehicle's simple control system and the complex task of identifying optimal driving conditions. The cloud platform processes vehicle profile data, road condition information, and traffic patterns to generate optimization recommendations, which are then transmitted back to the vehicle. This allows the vehicle to access advanced analytics without embedding complex processing capabilities in the vehicle itself.
Solution Approach 2:
The system pre-generates optimal driving condition profiles in the cloud based on historical data, weather patterns, and road characteristics before the vehicle encounters specific situations. When the vehicle needs guidance, it queries the pre-computed optimal conditions rather than performing real-time complex analysis, reducing on-vehicle computational requirements.
2Reliability
If the system does not maintain comprehensive vehicle profiles and real-time data analysis, then the system requires less computational resources, but safety issues such as tailgating and inadequate responses to road conditions occur
Solution Approach 1:
The patent divides the computational workload into segments: the vehicle's onboard system handles immediate sensor data collection and basic control functions, while the cloud computing platform handles complex profile analysis, trend identification, and optimal condition calculation. This segmentation allows safety-critical functions to be distributed across systems with appropriate computational capabilities.
Solution Approach 2:
The system continuously monitors actual driving conditions and compares them against the identified optimal conditions, providing feedback to adjust vehicle parameters. This feedback loop ensures safety by constantly verifying that the vehicle is operating under optimal conditions while using energy-efficient processing for routine comparisons.
3Ease of operation
If the system adjusts vehicle settings in real-time based on identified trends, then the system responds appropriately to road conditions, but the system requires complex real-time processing capabilities
Solution Approach 1:
The cloud computing platform serves as an intermediary that performs the complex real-time processing of trend analysis and optimal condition identification. The vehicle's onboard system receives processed recommendations from the cloud and executes them through simple control commands, avoiding the need for complex real-time processing capabilities within the vehicle itself.
Data Source
AI summary
A method, a system, and non-transitory computer readable medium for controlling an autonomous vehicle are provided. The method includes identifying a trend for an autonomous vehicle based on autonomous vehicle profiles associated with one or more vehicles within a network, identifying optimal driving conditions for the autonomous vehicle based on the trend; and controlling one or more subsystems of the autonomous vehicle based on the identified optimal driving conditions.