UAV Vision Chip RTOS Linux Synchronization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Unmanned aerial vehicles (UAVs) face inaccurate data collection due to the non-real-time processing of flight control data and image data, leading to poor control accuracy, as the Linux operating system used in UAVs has significant fluctuations, resulting in delayed processing of flight control data.
Innovation Solution
Implementing a vision chip with a real-time operating system that generates a trigger signal to collect flight control data and image sequences synchronously, synchronizing the time of the main operating system with the real-time operating system, and performing visual processing to ensure accurate and simultaneous collection of flight control data and image sequences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the Linux operating system is used for visual processing in the UAV, then the system can perform general-purpose processing, but the data collection accuracy deteriorates due to time fluctuations exceeding 20ms
Solution Approach 1:
The system is segmented into two independent operating systems: a real-time operating system (RTOS) dedicated to flight control data collection with sub-millisecond precision, and a main Linux operating system for visual processing. This segmentation allows each system to optimize for its specific function, resolving the contradiction between general-purpose capability and measurement precision.
Solution Approach 2:
The RTOS acts as an intermediary between the image sensor and the Linux system. It collects flight control data and image data synchronously with millisecond-level timing, then transmits this synchronized data to the Linux system for visual processing, ensuring accurate temporal correlation without burdening the Linux system with real-time constraints.
2Adaptability or versatility
If the Linux operating system processes flight control data, then visual processing can be performed, but the real-time control performance deteriorates due to processing delays
Solution Approach 1:
The system separates real-time control functions from visual processing functions by running them on different operating systems. The RTOS handles time-critical flight control data collection and transmission with deterministic timing, while the Linux system performs computationally intensive visual processing, eliminating the speed bottleneck.
Solution Approach 2:
The real-time data collection and transmission functionality is extracted from the Linux system and implemented as an independent RTOS. This extraction removes the real-time performance constraints from the visual processing pipeline, allowing Linux to focus solely on image analysis without being burdened by timing requirements.
3Ease of operation
If flight control data and image data are collected without synchronization, then data collection simplicity is maintained, but the control accuracy deteriorates due to time differences between data points
Solution Approach 1:
The RTOS merges the collection of flight control data and image data into a single synchronized sampling process. Both types of data are collected simultaneously at the same time points, ensuring perfect temporal alignment while maintaining a simple unified collection mechanism managed by the real-time system.
Solution Approach 2:
The system implements timestamp feedback for each data point collected by the RTOS. These timestamps are attached to both flight control data and image data, enabling the Linux system to verify synchronization and perform time-correlated analysis, ensuring control accuracy through explicit temporal information.
Data Source
AI summary
The present invention discloses a data collection method, an unmanned aerial vehicle (UAV) and a storage medium. The method is used for a vision chip of the UAV, the vision chip including a main operating system and a real-time operating system, and the method includes: generating, by the real-time operating system, a trigger signal; collecting, by the real-time operating system based on the trigger signal, flight control data of the UAV and controlling an image sensor to collect an image sequence; synchronizing, by the real-time operating system, a time of the main operating system with a time of the real-time operating system; and performing, by the main operating system, visual processing on the flight control data and the image sequence, to ensure that the flight control data and the image sequence are collected synchronously. By using the method, accuracy of data collected during controlling of the UAV can be improved.