Autonomous UAV Interaction Using Shared Virtual Environment Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous aerial vehicle technologies face challenges in efficiently navigating and tracking objects in complex environments, particularly in real-time, due to limitations in perception and object tracking systems, which affect their ability to perform tasks like autonomous flight and image capture.
Innovation Solution
The implementation of a navigation system that utilizes multiple image capture devices and sensors to generate perception inputs, fuse data from various sources, and employ machine learning models for object detection and tracking, allowing for real-time object tracking and autonomous navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous aerial vehicle uses multiple image capture devices and sensors for navigation, then measurement precision and reliability improve, but device complexity increases
Solution Approach 1:
The navigation system is divided into specialized modules: perception input generation from multiple image capture devices, data fusion processing, and machine learning-based object detection and tracking. Each module handles specific tasks independently, improving measurement precision while managing system complexity through functional segmentation.
Solution Approach 2:
Multiple image capture devices and sensors are merged into a unified navigation system that processes data together. The system combines inputs from various sensors and applies machine learning models to achieve accurate real-time object detection and tracking, improving reliability through data fusion.
2Productivity
If autonomous aerial vehicle processes perception inputs in real-time for object tracking, then productivity improves, but use of energy increases
Solution Approach 1:
The system performs preliminary data fusion of perception inputs from multiple sensors before object detection and tracking. By pre-processing and organizing sensor data in advance, the machine learning models can operate more efficiently with structured inputs, reducing real-time computational energy consumption while maintaining productivity.
Solution Approach 2:
The system uses machine learning models that create simplified representations or copies of objects based on sensor data. These models process perceptual information efficiently by working with extracted features rather than raw sensor data, enabling real-time tracking with reduced energy consumption.
Data Source
AI summary
A technique for user interaction with an autonomous unmanned aerial vehicle (UAV) is described. In an example embodiment, perception inputs from one or more sensor devices are processed to build a shared virtual environment that is representative of a physical environment. The sensor devices used to generate perception inputs can include image capture devices onboard an autonomous aerial vehicle that is in flight through the physical environment. The shared virtual environment can provide a continually updated representation of the physical environment which is accessible to multiple network-connected devices, including multiple UAVs and multiple mobile computing devices. The shared virtual environment can be used, for example, to display visual augmentations at network-connected user devices and guide autonomous navigation by the UAV.