Active auditory positioning method for map-free navigation

A positioning method and auditory technology, applied in the field of information science, can solve the problems of poor real-time performance, obstacles blocking the field of view, and has not been introduced into robots without map navigation, etc., to achieve good fusion effect and high application value.

Pending Publication Date: 2022-05-31
PEKING UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Previous work has shown that the cost of wifi-based positioning and visible light communication is relatively low, but it requires external receivers for the target and indoor environment with wifi hotspots or LED lights
The vision-based target positioning method is flexible, and can handle various targets according to the semantic type; however, there are problems such as obstacle occlusion and field of view, and the real-time performance is not good.
[0004] To the best of our knowledge, auditory-based active localization has not been introduced into the study of robotic mapless navigation

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Active auditory positioning method for map-free navigation
  • Active auditory positioning method for map-free navigation
  • Active auditory positioning method for map-free navigation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to enable the mobile robot to realize collision-free navigation in the actual unknown scene, the present invention proposes an active sound source localization technology for mapless navigation. The present invention proposes a target-oriented end-to-end navigation model for robot platforms through reinforcement learning. The model can learn a complex policy: the robot chooses how to move based on environmental information, including raw 2D laser ranging results and object positions. At the same time, in order to apply the model trained in the simulation environment to the real environment, we set up active auditory positioning to determine the relative position of the target. figure 1 It shows how the robot continuously determines the target position by adjusting its own pose during the navigation process. figure 2 is the measurement error of the target position in different directions determined by the spherical microphone array. In order to quantitatively...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses an active auditory positioning method for map-free navigation. The active auditory positioning method comprises the following steps: 1) training a mobile robot navigation model on a simulation platform through a reinforcement learning method; 2) the mobile robot collects distance measurement information of the laser radar at the current moment according to a set time step length, and obtains auditory orientation information and pose information of a speedometer of the mobile robot based on a sound source of a target position; wherein the laser radar is carried on the mobile robot; and 3) inputting the distance measurement information, the auditory orientation information and the pose information into the mobile robot navigation model trained in the step 1) to deduce a speed instruction at the current moment, and navigating the mobile robot to a target position according to the speed instruction. According to the method, a more reliable and effective target positioning mode is adopted, and the method has high application value for map-free navigation of a real scene.

Description

technical field [0001] The invention belongs to the field of information science and relates to an auditory positioning method, in particular to an active auditory positioning method used for mapless navigation of a mobile robot. Background technique [0002] So far, robots have created enormous value in fields such as industrial manufacturing, home services, interstellar exploration, and military reconnaissance. Compared with visual information mobile robot navigation methods, auditory perception-based robot navigation has advantages in protecting privacy. In addition, auditory localization can provide additional information to help the robot determine the target when the target is not in the robot's field of view or blocked by obstacles. The autonomous navigation of the mobile robot refers to the movement process that the mobile robot perceives the external environment through the sensor and combines its own state to reach the target point without collision. Mobile robot...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01C21/34G01C22/00G01S17/08G01S17/931G01S5/18G01S5/24
CPCG01C21/3407G01C21/3446G01C22/00G01S17/08G01S17/931G01S5/186G01S5/24
Inventor 罗定生吴玺宏方帅张佳男林惟凯刘天林
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap