http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-107345927-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N27-00 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N27-00 |
| filingDate | 2017-06-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2021-02-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2021-02-19-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-107345927-B |
| titleOfInvention | Medium material recognition device for autonomous environment perception of robot |
| abstract | The invention discloses a medium material identification method for autonomous environment perception of a robot, and belongs to the field of material identification. The invention comprises the following steps: driving the metal electrode to contact and separate with the material to be detected for multiple times, and detecting an electrostatic sensing signal generated by the change of the induced charge of the metal electrode through an electrostatic measurement system to obtain electrostatic signals of various materials; extracting a static signal charge leakage factor, the number of effective negative peaks, the variance of positive and negative peak values in a time window and three characteristic quantities; constructing a classifier by using the combined feature vector and adopting a k nearest neighbor algorithm to carry out identification and classification; and (4) re-collecting the electrostatic signals of a certain class of materials, and identifying and classifying the signals by using a trained classifier to realize automatic identification and classification of the materials by the robot. The invention relates to a medium material identification method for autonomous environment perception of a robot, which has the characteristics of no influence of illumination conditions, reliable principle and simple structure because of no need of an external excitation measurement mode. |
| priorityDate | 2017-01-21-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 13.