ADAS Training Route Adjustment for Real-Time Scenario Data Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle imaging systems face challenges in efficiently collecting large amounts of data required for advanced driving assistance systems (ADAS) performance testing, leading to costly and time-consuming repeat data collection drives when KPIs are not met.
Innovation Solution
An online scenario detector preprocesses sensor data in real-time to identify scenarios and adjust vehicle routes dynamically to optimize data collection, ensuring completion of key performance indicators (KPIs) during a single drive.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional data collection methods are used without real-time optimization, then the data collection process is simple to implement, but the productivity and efficiency of data collection are low due to the need for multiple repeat drives
Solution Approach 1:
The system continuously monitors sensor data collection progress and compares it against target KPIs in real-time. Based on this feedback, the route optimization module dynamically adjusts the vehicle route to ensure KPI completion, transforming a static data collection process into an adaptive closed-loop system that improves productivity
Solution Approach 2:
The patent transforms the static, pre-planned data collection route into a dynamic route that can be adjusted in real-time. The route optimization module modifies the vehicle path based on current data collection status, environmental conditions, and KPI requirements, enabling the system to adapt to changing conditions and maximize data collection efficiency
2Quantity of substance
If multiple repeat data collection drives are conducted to meet KPIs, then the target data quantity can be achieved, but the loss of time and increase in costs occur
Solution Approach 1:
The system performs preliminary analysis of the current route's data collection potential and predicts whether KPIs will be met. By proactively identifying routes that are unlikely to satisfy KPIs before completion, the system can make early route adjustments rather than completing entire unnecessary drives, significantly reducing time loss
Solution Approach 2:
Real-time monitoring of data collection progress against target KPIs provides continuous feedback. When the system detects that current progress is insufficient to meet KPIs, it triggers route reoptimization to redirect the vehicle toward more productive data collection opportunities, preventing wasted time on unproductive drives
3Productivity
If real-time route optimization is implemented to optimize data collection, then the productivity and efficiency improve, but the device complexity and computational requirements increase
Solution Approach 1:
The route optimization system is segmented into distinct functional modules: KPI determination module, data collection status monitoring module, and route optimization module. This modular architecture distributes computational complexity across separate components, making the overall system more manageable and easier to implement while maintaining real-time optimization capabilities
Solution Approach 2:
The route optimization module acts as an intermediary between the data collection status monitoring and the vehicle control systems. It processes complex optimization calculations and translates them into actionable route adjustments, shielding the rest of the system from computational complexity while enabling real-time productivity improvements
4Reliability
If the vehicle route is dynamically adjusted during data collection, then the completeness of KPI achievement improves, but the ease of operation decreases due to continuous route changes
Solution Approach 1:
The system provides continuous feedback to the driver about KPI completion status and proposed route changes. This transparency allows the driver to understand the rationale behind route adjustments and make informed decisions, maintaining operational ease while improving KPI completion reliability through collaborative human-machine operation
Data Source
AI summary
A vehicular training system includes a sensor disposed at a vehicle and sensing exterior of the vehicle. The sensor is operable to capture sensor data. An electronic control unit (ECU) includes electronic circuitry and associated software, with the electronic circuitry of the ECU including a data processor for processing sensor data captured by the sensor. The vehicular training system, while the vehicle travels along the route for the data collection drive and while the sensor captures sensor data, compares a quantity of sensor data that is captured to a target quantity of sensor data to be captured by the vehicular training system for training an advanced driving assistance system. The vehicular training system adjusts the route of the vehicle based at least in part on comparison of the quantity of sensor data that is captured and the target quantity of sensor data.