Indoor Robot Localization Using RF Labels and Odometry Error Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing odometry localization methods for indoor inspection robots suffer from significant errors due to complex indoor environmental factors, leading to inaccurate trajectory prediction and low inspection efficiency.
Innovation Solution
A neural network-based method for calibration and localization that employs RF signal sources, log-normal propagation loss modeling, and a generalized linear model to compute actual robot coordinates, combined with a neural network for odometry error modeling and backpropagation training to optimize the predicted path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If odometry localization method is used for indoor inspection robot, then the robot can perform autonomous navigation, but the localization accuracy deteriorates due to accumulated trajectory error and computational error from complex indoor environmental factors
Solution Approach 1:
The patent introduces RFID label signal sources as intermediary objects in the environment. The inspection robot's reader-writer receives RF signals from these labels to compute actual coordinates, serving as a mediator between the robot and the environment for accurate localization without relying solely on odometry
Solution Approach 2:
The patent replaces the mechanical odometry-based localization system with an RF signal-based localization system. Instead of relying on wheel-based odometry that accumulates errors, the system uses radio frequency signal reception and log-normal propagation loss modeling to determine robot position
2Measurement precision
If RF signal-based localization is implemented using log-normal propagation loss model, then localization accuracy is improved, but the system complexity increases due to multiple signal sources and computational models
Solution Approach 1:
The patent makes the reader-writer device multi-functional by enabling it to perform both its original function (reading/writing RFID tags) and localization function (receiving RF signals from label sources and computing robot coordinates based on signal strength and propagation loss model)
Solution Approach 2:
The patent changes the operational parameters of the reader-writer by configuring it to receive RF signals from multiple label signal sources and process signal strength information (P(d)) through the log-normal propagation loss model to compute distance and coordinates, transforming it into a localization sensor
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
This approach significantly enhances localization accuracy by minimizing odometry errors, allowing for precise path prediction and improved inspection efficiency in various indoor environments, including complex settings.
Implementation Method 1
establishing a log-normal propagation loss model according to a signal strength of received labels: P(d)=P(d0)−10α log(d/d0)−xσ
Implementation Method 2
providing a reader-writer for receiving the signals of the label signal sources on an indoor robot
Data Source
AI summary
The present disclosure provides a neural network-based method for calibration and localization of an indoor inspection robot. The method includes the following steps: presetting positions for N label signal sources capable of transmitting radio frequency (RF) signals; computing an actual path of the robot according to numbers of signal labels received at different moments; computing positional information moved by the robot at a tth moment, and computing a predicted path at the tth moment according to the positional information; establishing an odometry error model with the neural network and training the odometry error model; and inputting the predicted path at the tth moment to a well-trained odometry error model to obtain an optimized predicted path. The present disclosure maximizes the localization accuracy for the indoor robot by minimizing the error of the odometer with the odometry calibration method.