Frequency-Temporal Disagreement Adaptation for Robotic Terrain Classification via Vibration in a Dynamic Environment
The accurate terrain classification in real time is of great importance to an autonomous robot working in field, because the robot could avoid non-geometric hazards, adjust control scheme, or improve localization accuracy, with the aid of terrain classification. In this paper, we investigate the vib...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/22/6550 |
| _version_ | 1797547714067562496 |
|---|---|
| author | Chen Cheng Ji Chang Wenjun Lv Yuping Wu Kun Li Zerui Li Chenhui Yuan Saifei Ma |
| author_facet | Chen Cheng Ji Chang Wenjun Lv Yuping Wu Kun Li Zerui Li Chenhui Yuan Saifei Ma |
| author_sort | Chen Cheng |
| collection | DOAJ |
| description | The accurate terrain classification in real time is of great importance to an autonomous robot working in field, because the robot could avoid non-geometric hazards, adjust control scheme, or improve localization accuracy, with the aid of terrain classification. In this paper, we investigate the vibration-based terrain classification (VTC) in a dynamic environment, and propose a novel learning framework, named DyVTC, which tackles online-collected unlabeled data with concept drift. In the DyVTC framework, the exterior disagreement (ex-disagreement) and interior disagreement (in-disagreement) are proposed novely based on the feature diversity and intrinsic temporal correlation, respectively. Such a disagreement mechanism is utilized to design a pseudo-labeling algorithm, which shows its compelling advantages in extracting key samples and labeling; and consequently, the classification accuracy could be retrieved by incremental learning in a changing environment. Since two sets of features are extracted from frequency and time domain to generate disagreements, we also name the proposed method feature-temporal disagreement adaptation (FTDA). The real-world experiment shows that the proposed DyVTC could reach an accuracy of 89.5%, but the traditional time- and frequency-domain terrain classification methods could only reach 48.8% and 71.5%, respectively, in a dynamic environment. |
| first_indexed | 2024-03-10T14:49:07Z |
| format | Article |
| id | doaj.art-b585b2905bec4291b3c1aab3fc5f3e73 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T14:49:07Z |
| publishDate | 2020-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-b585b2905bec4291b3c1aab3fc5f3e732023-11-20T21:10:47ZengMDPI AGSensors1424-82202020-11-012022655010.3390/s20226550Frequency-Temporal Disagreement Adaptation for Robotic Terrain Classification via Vibration in a Dynamic EnvironmentChen Cheng0Ji Chang1Wenjun Lv2Yuping Wu3Kun Li4Zerui Li5Chenhui Yuan6Saifei Ma7Department of Automation, University of Science and Technology of China, Hefei 230027, ChinaDepartment of Automation, University of Science and Technology of China, Hefei 230027, ChinaDepartment of Automation, University of Science and Technology of China, Hefei 230027, ChinaKey Laboratory of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, ChinaDepartment of Automation, University of Science and Technology of China, Hefei 230027, ChinaDepartment of Automation, University of Science and Technology of China, Hefei 230027, ChinaInstitute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei 230088, ChinaInstitute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei 230088, ChinaThe accurate terrain classification in real time is of great importance to an autonomous robot working in field, because the robot could avoid non-geometric hazards, adjust control scheme, or improve localization accuracy, with the aid of terrain classification. In this paper, we investigate the vibration-based terrain classification (VTC) in a dynamic environment, and propose a novel learning framework, named DyVTC, which tackles online-collected unlabeled data with concept drift. In the DyVTC framework, the exterior disagreement (ex-disagreement) and interior disagreement (in-disagreement) are proposed novely based on the feature diversity and intrinsic temporal correlation, respectively. Such a disagreement mechanism is utilized to design a pseudo-labeling algorithm, which shows its compelling advantages in extracting key samples and labeling; and consequently, the classification accuracy could be retrieved by incremental learning in a changing environment. Since two sets of features are extracted from frequency and time domain to generate disagreements, we also name the proposed method feature-temporal disagreement adaptation (FTDA). The real-world experiment shows that the proposed DyVTC could reach an accuracy of 89.5%, but the traditional time- and frequency-domain terrain classification methods could only reach 48.8% and 71.5%, respectively, in a dynamic environment.https://www.mdpi.com/1424-8220/20/22/6550autonomous robotnon-geometric hazardsterrain classificationdynamic environmentvibration |
| spellingShingle | Chen Cheng Ji Chang Wenjun Lv Yuping Wu Kun Li Zerui Li Chenhui Yuan Saifei Ma Frequency-Temporal Disagreement Adaptation for Robotic Terrain Classification via Vibration in a Dynamic Environment Sensors autonomous robot non-geometric hazards terrain classification dynamic environment vibration |
| title | Frequency-Temporal Disagreement Adaptation for Robotic Terrain Classification via Vibration in a Dynamic Environment |
| title_full | Frequency-Temporal Disagreement Adaptation for Robotic Terrain Classification via Vibration in a Dynamic Environment |
| title_fullStr | Frequency-Temporal Disagreement Adaptation for Robotic Terrain Classification via Vibration in a Dynamic Environment |
| title_full_unstemmed | Frequency-Temporal Disagreement Adaptation for Robotic Terrain Classification via Vibration in a Dynamic Environment |
| title_short | Frequency-Temporal Disagreement Adaptation for Robotic Terrain Classification via Vibration in a Dynamic Environment |
| title_sort | frequency temporal disagreement adaptation for robotic terrain classification via vibration in a dynamic environment |
| topic | autonomous robot non-geometric hazards terrain classification dynamic environment vibration |
| url | https://www.mdpi.com/1424-8220/20/22/6550 |
| work_keys_str_mv | AT chencheng frequencytemporaldisagreementadaptationforroboticterrainclassificationviavibrationinadynamicenvironment AT jichang frequencytemporaldisagreementadaptationforroboticterrainclassificationviavibrationinadynamicenvironment AT wenjunlv frequencytemporaldisagreementadaptationforroboticterrainclassificationviavibrationinadynamicenvironment AT yupingwu frequencytemporaldisagreementadaptationforroboticterrainclassificationviavibrationinadynamicenvironment AT kunli frequencytemporaldisagreementadaptationforroboticterrainclassificationviavibrationinadynamicenvironment AT zeruili frequencytemporaldisagreementadaptationforroboticterrainclassificationviavibrationinadynamicenvironment AT chenhuiyuan frequencytemporaldisagreementadaptationforroboticterrainclassificationviavibrationinadynamicenvironment AT saifeima frequencytemporaldisagreementadaptationforroboticterrainclassificationviavibrationinadynamicenvironment |