A method for odor source localization based on adaptive spatial perception information.

By using an adaptive spatial perception information orientation method, combined with a Bayesian framework and particle swarm optimization algorithm, the problem of low odor source localization efficiency in turbulent environments is solved, and fast and accurate odor source localization is achieved.

CN117863183BActive Publication Date: 2026-05-26HEBEI UNIV OF TECH
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HEBEI UNIV OF TECH
Filing Date
2024-01-25
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing odor source localization methods are inefficient in turbulent environments and are prone to getting trapped in local optima, making it difficult to quickly and accurately locate odor sources.

Method used

An adaptive spatial sensing information-oriented approach is adopted, which uses a Bayesian framework to perform inference calculations on gas diffusion models and measurement data. The movement step size is adjusted by combining information entropy, and the adaptive information parameters are optimized by a particle swarm optimization algorithm with cosine random inertial weights to achieve the shortest search path.

Benefits of technology

It improves the efficiency and accuracy of odor source localization, avoids getting stuck in local optima during the search process, and adapts to the search needs of different scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117863183B_ABST
    Figure CN117863183B_ABST
Patent Text Reader

Abstract

This invention discloses an odor source localization method based on adaptive spatial perception information. The method includes the following steps: First, the search environment is divided into a fine grid, and a gas diffusion model that fits the actual scene is established to obtain the predicted concentration for each grid. Then, the real-time gas sampling data from the robot is binarized, and a sensor response model based on Poisson distribution is established to obtain the sampling concentration. The robot performs Bayesian inference using the predicted and sampled concentrations to update the likelihood function, thereby obtaining the posterior probability density function of the entire map. The reward function for each movable direction in the allowable action set is calculated using the posterior probability density function. The robot finds the direction with the largest change in the reward function, calculates the movement step size based on the current information entropy, and moves the robot a specified step size in the direction with the largest change in the reward function. This method solves the problems of existing odor source localization strategies easily getting trapped in local optima and the low search efficiency of fixed step sizes.
Need to check novelty before this filing date? Find Prior Art