US 12,449,403 B2
Floor material identification method, system and device, and storage medium
Tao Sun, Suzhou (CN); Liping Hu, Suzhou (CN); Wenhao Wang, Suzhou (CN); Xiaoying Lu, Suzhou (CN); Qingdong Zhou, Suzhou (CN); Zhian Yu, Suzhou (CN); and Fuping Cheng, Suzhou (CN)
Assigned to MIDEA ROBOZONE TECHNOLOGY CO., LTD., Suzhou (CN)
Appl. No. 18/026,817
Filed by MIDEA ROBOZONE TECHNOLOGY CO., LTD., Suzhou (CN)
PCT Filed Feb. 25, 2021, PCT No. PCT/CN2021/077834
§ 371(c)(1), (2) Date Mar. 16, 2023,
PCT Pub. No. WO2022/057209, PCT Pub. Date Mar. 24, 2022.
Claims priority of application No. 202010983034.2 (CN), filed on Sep. 17, 2020.
Prior Publication US 2023/0324343 A1, Oct. 12, 2023
Int. Cl. G01N 29/12 (2006.01); G01N 29/46 (2006.01); G06F 18/214 (2023.01)
CPC G01N 29/12 (2013.01) [G01N 29/46 (2013.01); G06F 18/214 (2023.01); G01N 2291/023 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A floor material identification method, applied in a cleaning robot, the floor material identification method comprising:
acquiring a vibration signal generated by a cleaning robot when operating on a floor of a material among a plurality of materials;
setting a predetermined low frequency band range and a predetermined high frequency band range, both selected from a frequency band range for the vibration signal;
determining low frequency band energy and high frequency band energy of the vibration signal based on the predetermined low frequency band range and the predetermined high frequency band range;
determining a ratio of the low frequency band energy to the high frequency band energy as an identification feature;
obtaining at least one identification parameter by inputting the identification feature into a classifier for training; and
identifying a floor material type based on the at least one identification parameter.