Robotic H Matrix Creation for Wi-Fi Motion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Wi-Fi motion detection systems lack effective training methods to accurately identify human activities and locations, as they rely on software-based monitoring algorithms that struggle to differentiate between various human movements and environments.
Innovation Solution
A robotic training system is introduced, comprising a training robot, modules for data collection and correction, and an IoT device database, which replicates human movements to generate precise frequency data for motion detection, integrating context data from IoT devices to enhance location and activity recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If software-based monitoring algorithms are used for motion detection, then the system can detect motion changes, but it struggles to accurately differentiate between various human movements and environments
Solution Approach 1:
The patent uses a robotic agent to physically copy and perform human movements in the target environment. The robot executes trained movements that replicate human activities, allowing the system to collect training data by observing the actual Wi-Fi signal changes caused by these replicated movements. This copying approach enables accurate differentiation between various human movements by capturing the unique signal patterns each movement produces.
Solution Approach 2:
The system performs preliminary training actions by having the robotic agent learn and store trained movements in a training database before actual motion detection is needed. The robot pre-collects impulse response data for various human activities by performing these movements, creating a library of movement patterns that the system can later compare against during operational use. This preliminary action prepares the system to accurately differentiate movements without requiring real-time learning.
2Measurement precision
If a robotic agent is used to replicate human movements for training, then precise frequency data can be generated, but the system complexity increases
Solution Approach 1:
The robotic agent serves multiple functions within the system: it performs trained movements to collect training data, executes impulse response measurements, and operates in different target environments. This multi-functionality reduces the need for separate specialized devices for each task, thereby managing system complexity while maintaining measurement precision through a single versatile platform.
Solution Approach 2:
The robotic agent autonomously performs trained movements and collects its own training data without requiring manual intervention for each measurement. The system self-manages the data collection process by having the robot independently execute movements, capture Wi-Fi signal changes, and store impulse response data, reducing the operational complexity of data acquisition.
3Quantity of substance
If IoT device data is integrated to augment training data, then a larger library of profiles can be created, but data integration complexity increases
Solution Approach 1:
The patent merges data from multiple sources including robotic agent measurements and IoT device observations into a unified training database. By combining impulse response data from the robot with contextual information from IoT devices, the system creates a comprehensive profile library that leverages the strengths of both data sources while managing integration through a centralized database structure.
Solution Approach 2:
The system uses an intermediary data integration layer that processes and harmonizes data from diverse sources before storing it in the training database. This intermediary layer standardizes data formats and resolves conflicts between different data sources, enabling the creation of a large profile library without proportionally increasing integration complexity through systematic data management.
Data Source
AI summary
Systems and methods of using a robot to train the system for motion detection are provided. A simple robot can be put in a room and programmed not to move except in accordance with specific programmed command. Such commands may be sent to the robot regarding movement(s) at a certain rate than could be seen in the response to a channel. A data set may be built over time, where the robot may be programmed to move such that the robot does change at specific times in duration and amount. Such robot motion may also be iterated. The algorithm records the impulse response changes associated with the robot changes and a database may be built based on such recorded and associated changes.