TOA-Based Guidance Learning for Lightweight Obstacle Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current navigation systems for unmanned aerial vehicles (UAVs) that process images to identify obstacles are expensive and computationally intensive, making them impractical for commercial and recreational use due to the need for high-end processing systems and significant weight, which limits their computational power for real-time object location determination.
Innovation Solution
A machine learning system, referred to as the Sense and Guide Machine Learning (SGML) system, is trained using time-of-arrival (TOA) information to determine object locations, allowing for lightweight on-board computing and reducing computational expense by generating guidance information in real-time, thus enabling effective guidance without the need for expensive image processing systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image processing systems are used to identify obstacles, then obstacle detection accuracy is improved, but system cost and weight increase significantly
Solution Approach 1:
The patent replaces complex mechanical image processing systems with an acoustic field-based sensor array system. Instead of using cameras and computational image analysis, the system uses acoustic sensors to detect objects through sound wave reflections, thereby reducing mechanical complexity and weight while maintaining detection capability
Solution Approach 2:
The patent creates a computational model (virtual copy) of the acoustic environment that simulates object locations based on time-of-arrival data. This allows the system to determine object positions through mathematical modeling rather than physical image processing, reducing the need for heavy computational hardware
2Productivity
If high-end processing systems are used to process images in real time, then real-time obstacle identification is improved, but system cost and power consumption increase
Solution Approach 1:
The patent substitutes computationally intensive image processing algorithms with simpler acoustic signal processing and mathematical optimization. The system processes time-of-arrival data from acoustic sensors using efficient algorithms that require minimal computational power, enabling real-time operation on low-power platforms
Solution Approach 2:
The patent changes the fundamental measurement parameter from visual image data to acoustic time-of-arrival data. This parameter change enables the use of simpler, faster processing algorithms that are computationally efficient and suitable for real-time operation on energy-constrained mobile platforms
3Measurement precision
If complex algorithms are used to determine object locations from sensor data, then location accuracy is improved, but computational expense increases
Solution Approach 1:
The patent extracts only the essential information (time-of-arrival of acoustic signals) needed for location determination, discarding unnecessary data. This extraction approach simplifies the computational problem from analyzing complex sensor patterns to solving a straightforward optimization problem based on timing data alone
Solution Approach 2:
The patent performs preliminary calculations of expected time-of-arrival values based on assumed object locations before comparing with actual measurements. This pre-computation approach simplifies the optimization process by providing a reference framework that reduces the complexity of the location determination algorithm
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The SGML system provides efficient and lightweight guidance for UAVs by determining object locations and generating guidance instructions in real-time, reducing the computational burden and weight, making it suitable for various autonomous platforms, including UAVs, unmanned ground vehicles, and unmanned space vehicles.
Implementation Method 1
The sensor array includes transmitters that transmit signals at intervals and receivers that collects return signals, which are transmitted signals reflected by objects
Implementation Method 2
The time-of-arrival of each return pulse represent the time between the transmitting of a signal and receiving of a return pulse
Data Source
AI summary
A system for generating a machine learning system to generate guidance information based on locations of objects is provided. The system accesses training data that includes training time-of-arrival (“TOA”) information of looks and guidance information for each look. The guidance information is based on a training collection of object locations. The TOA of a look represents, for each object location of a training collection of object locations, times between signals transmitted by transmitters and return signals received by receivers. The return signals represent signals reflected from an object at the object location. The system trains a machine learning system using the training data wherein the machine learning system inputs TOA information and outputs guidance information.