Navigation map updating method and apparatus and robot using the same

Patent metadata

Field	Value
Publication number	US-2021190513-A1
Application number	US-202016843923-A
Country	US
Kind code	A1
Filing date	Apr 9, 2020
Priority date	Dec 20, 2019
Publication date	Jun 24, 2021
Grant date	—

Abstract

The present disclosure discloses a navigation map updating method as well as an apparatus, and a robot using the same. The method includes: controlling a robot to move along a designated path after a successful relocalization of the robot, and recording key frame data of each frame on the designated path and a corresponding pose; creating a new navigation map, and copying information in an original navigation map into the new navigation map; and covering the key frame data of each frame on the designated path onto the new navigation map to obtain an updated navigation map. In this manner, there is no need for the user to manipulate the robot to recreate the map at the environment where the robot is operated, which saves a lot of time and manpower.

First claim

What is claimed is:

1 . A computer-implemented navigation map updating method for a robot, comprising executing on a processor steps of:
controlling the robot to move along a designated path after a successful relocalization of the robot, and recording key frame data of each frame on the designated path and a corresponding pose; creating a new navigation map, and copying information in an original navigation map into the new navigation map; and covering the key frame data of each frame on the designated path onto the new navigation map to obtain an updated navigation map.

2 . The method of claim 1 , wherein the step of recording the key frame data of each frame on the designated path and the corresponding pose comprises:
collecting the key frame data of a first frame, and determining a pose and an odometer value of the key frame data of the first frame, wherein the key frame data of the first frame is laser data of the first frame after the successful relocalization; collecting laser data of a current frame at a preset data collection frequency, and determining an odometer value of the laser data of the current frame; calculating an estimated pose of the laser data of the current frame based on the odometer value of the laser data of the current frame and a pose and an odometer value of laser data of a previous frame of the current frame; determining whether the laser data of the current frame is the key frame data of a new frame base on the estimated pose of the laser data of the current frame and a pose of reference key frame data, wherein the reference key frame data is the key frame data of the previous frame; and matching the estimated pose of the laser data of the current frame with a preset probability grid map to obtain a precise pose of the laser data of the current frame, in response to the laser data of the current frame being the key frame data of the new frame.

3 . The method of claim 2 , wherein the step of determine whether the laser data of the current frame is the key frame data of the new frame base on the estimated pose of the laser data of the current frame and the pose of the reference key frame data comprises:
calculating a distance difference and an angle difference between the estimated pose of the laser data of the current frame and the pose of the reference key frame data; and determining the laser data of the current frame as the key frame data of the new frame, in response to the distance difference being greater than a preset distance threshold or the angle difference being greater than a preset angle threshold.

4 . The method of claim 2 , wherein the step of matching the estimated pose of the laser data of the current frame with the preset probability grid map to obtain the precise pose of the laser data of the current frame comprises:
using the estimated pose of the laser data of the current frame as an initial coordinate to perform an optimization matching with respect to the probability grid map so as to obtain the precise pose of the laser data of the current frame, in response to the accuracy of an odometer of the robot being greater than a preset accuracy threshold.

5 . The method of claim 2 , wherein the step of matching the estimated pose of the laser data of the current frame with the preset probability grid map to obtain the precise pose of the laser data of the current frame comprises:
using the estimated pose of the laser data of the current frame as the initial coordinate to perform one of an ICP matching and a template matching with respect to the probability grid map so as to obtain a first precise coordinate of the laser data of the current frame; and using the first precise coordinate of the laser data of the current frame as the initial coordinate to perform an optimization matching with respect to the probability grid map so as to obtain the precise pose of the laser data of the current frame.

6 . The method of claim 1 , wherein after the step of covering the key frame data of each frame on the designated path onto the new navigation map further comprises:
covering pixels outside a laser beam as first type pixels in response to the pixels outside the laser beam being not the first type pixels, wherein the first type pixels are pixels representing an unknown area.

7 . The method of claim 1 , wherein after the step of covering the key frame data of each frame on the designated path onto the new navigation map further comprises:
creating a new probability grid map, and copying information in original probability grid map into the new probability grid map; covering the key frame data of each frame on the designated path into the new probability grid map to obtain an updated probability grid map; denoising the updated navigation map based on the updated probability grid map to obtain a denoised navigation map.

8 . A navigation map updating apparatus for a robot, comprising:
a key frame data recording module configured to control the robot to move along a designated path after a successful relocalization of the robot, and record key frame data of each frame on the designated path and a corresponding pose; a navigation map copying module configured to create a new navigation map, and copy information in an original navigation map into the new navigation map; and a key frame data covering module configured to cover the key frame data of each frame on the designated path onto the new navigation map to obtain an updated navigation map.

9 . The apparatus of claim 8 , wherein the key frame data recording module comprises:
a first collection unit configured to collect the key frame data of a first frame, and determine a pose and an odometer value of the key frame data of the first frame, where the key frame data of the first frame is laser data of the first frame after the successful relocalization; a second collection unit configured to collect laser data of a current frame at a preset data collection frequency, and determine an odometer value of the laser data of the current frame; a pose estimation unit configured to calculate an estimated pose of the laser data of the current frame based on the odometer value of the laser data of the current frame and a pose and an odometer value of laser data of a previous frame of the current frame; a key frame determination unit configured to determine whether the laser data of the current frame is the key frame data of a new frame base on the estimated pose of the laser data of the current frame and a pose of reference key frame data, where the reference key frame data is the key frame data of the previous frame; and a map matching unit configured to match the estimated pose of the laser data of the current frame with a preset probability grid map to obtain a precise pose of the laser data of the current frame, in response to the laser data of the current frame being the key frame data of the new frame.

10 . The apparatus of claim 9 , wherein the key frame determination unit comprises:
a difference calculation subunit configured to calculate a distance difference and an angle difference between the estimated pose of the laser data of the current frame and the pose of the reference key frame data; and a key frame determination subunit configured to determine the laser data of the current frame as the key frame data of the new frame, in response to the distance difference being greater than a preset distance threshold or the angle difference being greater than a preset angle threshold.

11 . The apparatus of claim 9 , wherein the map matching unit comprises:
a first matching subunit configured to use the estimated pose of the laser data of the current frame as an initial

Assignees

• Ubtech Robotics Corp Ltd

Inventors

• Zhao Yongsheng
• Liu Zhichao
• Pang Jianxin
• Xiong Youjun

Classifications

• G01C21/3848

  Data obtained from both position sensors and additional sensors · CPC title

• G01C21/32 Primary

  Structuring or formatting of map data · CPC title

• G01S17/88

  Lidar systems specially adapted for specific applications · CPC title

• G01S17/875

  for determining attitude · CPC title

• G05D1/0272

  comprising means for registering the travel distance, e.g. revolutions of wheels (measuring distance traversed on the ground by vehicles, e.g. using odometers G01C22/00) · CPC title