Mobile Unit Control Model Updating via Targeted Sensor Tasks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated driving systems face challenges in consistently managing diverse driving situations, leading to suboptimal passenger comfort and route efficiency, and existing methods for data collection in complex environments are costly and time-consuming.
Innovation Solution
A method and system where a central control unit generates detection tasks for mobile units to collect specific sensor data, which are then used to update and optimize the control model through cooperative learning, allowing targeted data collection and efficient optimization of automatic driving functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If test drivers with specially equipped vehicles intentionally perform drives in problematic situations to collect data, then the control model can be improved, but the costs and time outlay increase significantly
Solution Approach 1:
The system enables automatic driving functions to self-optimize by autonomously detecting weaknesses, generating detection tasks, collecting relevant sensor data, and updating control models without requiring manual test driver intervention. This self-service mechanism eliminates the time-consuming and costly process of organized test drives while maintaining continuous improvement of the control model
Solution Approach 2:
The system implements a closed-loop feedback mechanism where the automatic driving function continuously monitors its own performance, identifies weaknesses in real-time, and uses this feedback to generate targeted detection tasks for data collection. This feedback-driven approach enables automatic optimization without manual intervention, resolving the contradiction between improvement quality and time investment
2Adaptability or versatility
If comprehensive data collection is performed to optimize automatic driving across all driving situations, then the control model coverage improves, but the data collection costs and complexity increase
Solution Approach 1:
Instead of uniformly collecting data across all driving situations, the system applies local quality by generating detection tasks that are specifically tailored to identified weaknesses and problematic situations. The detection tasks request only the specific sensor data relevant to the particular weakness being addressed, avoiding unnecessary data collection and reducing system complexity while maintaining comprehensive coverage where needed
Solution Approach 2:
The system dynamically changes detection parameters based on the identified weaknesses. Detection tasks are generated with specific conditions and parameters tailored to the particular driving situation and weakness type, allowing the system to adapt its data collection strategy to match the specific optimization needs rather than using a fixed, complex comprehensive collection approach
Data Source
AI summary
The invention relates to a method for updating a control model for automatic control of at least one mobile unit. A central control unit generates a detection task and transmits same to the mobile unit. The mobile unit comprises sensors, and the detection task comprises conditions for detecting sensor data sets by means of the sensors. The mobile unit detects the sensor data sets by means of the sensors using the detection task, generates transmission data using the detected sensor data sets, and transmits the transmission data to the central control unit. The central control unit receives the transmission data and generates an updated control model using the received transmission data. The system according to the invention for updating a control model for automatic control of at least one mobile unit comprises a central control unit by means of which a detection task may be generated and transmitted to the mobile unit. The mobile unit comprises sensors, and the detection task comprises conditions for detecting sensor data sets by means of the sensors. The sensor data sets may be detected by means of the sensors of the mobile unit using the detection task, transmission data may be generated using the detected sensor data sets, and the transmission data may be transmitted to the central control unit. In doing so, the central control unit may receive the transmission data, and an updated control model may be generated using the received transmission data.