Autonomous Navigation Activation Using Driver-Specific ML Prompts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advanced driver assistance systems (ADAS) struggle to seamlessly integrate and optimize the activation of autonomous driving features, leading to manual or erroneous vehicle operation, especially in environments with obstructions.
Innovation Solution
A system utilizing machine learning to track the utilization and performance of ADAS functions over time, determining the optimal timing to activate specific ADAS features, such as automated driving or parking, based on environmental conditions and vehicle state data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous navigation functions are activated in all environments, then automation coverage is improved, but safety and reliability deteriorate due to manual or erroneous operation in unsuitable conditions
Solution Approach 1:
The system dynamically changes operational parameters by adjusting the activation conditions of autonomous navigation based on environmental parameters detected by sensors. The machine learning model evaluates multiple environmental parameters (obstructions, road conditions, weather) to determine optimal activation conditions, thereby improving both automation coverage and safety by avoiding activation in unsuitable conditions
Solution Approach 2:
The system implements feedback mechanisms where the machine learning model continuously learns from historical driving data and sensor feedback to improve its determination of optimal activation conditions. The system monitors the performance and utilization of ADAS functions, using this feedback to refine its decisions about when to activate autonomous navigation, thereby improving reliability while maintaining automation coverage
2Measurement precision
If machine learning models are trained on extensive historical data to improve activation accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system segments the complex machine learning model into manageable components: sensor data acquisition module, historical data storage module, machine learning model module, and activation control module. This segmentation allows the system to achieve high measurement precision through comprehensive data analysis while managing device complexity through modular architecture, where each segment can be independently optimized and maintained
Data Source
AI summary
Controlling activation of an autonomous navigation function of a vehicle is provided. A system can include a data processing system with one or more processors, coupled to memory. The data processing system can determine, based on data collected from a vehicle and using a machine learning model trained on historical driving data associated with a driver of the vehicle and a driver having a driver profile corresponding to the historical driving data, that a vehicle controller of the vehicle is configured to autonomously navigate the vehicle through a scenario, facilitate, based on the collected data and the trained model, display of a prompt at the vehicle to activate autonomous navigation of the vehicle for the scenario, and upon receiving an indication of activation from the driver, provide instructions to the vehicle controller to perform autonomous driving control through the scenario, thereby reducing likelihood of error and lowering insurance premiums.