{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:04:54Z","timestamp":1753891494443,"version":"3.41.2"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T00:00:00Z","timestamp":1682467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073299","62076223"],"award-info":[{"award-number":["62073299","62076223"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Tactile object recognition (TOR) is very important for the accurate perception of robots. Most of the TOR methods usually adopt uniform sampling strategy to randomly select tactile frames from a sequence of frames, which will lead to a dilemma problem, i.e., acquiring the tactile frames with high sampling rate will get lots of redundant data, while the low sampling rate will miss important information. In addition, the existing methods usually adopt single time scale to construct TOR model, which will induce that the generalization capability is not enough for processing the tactile data generated under different grasping speeds. To address the first problem, a novel gradient adaptive sampling (GAS) strategy is proposed, which can adaptively determine the sampling interval according to the importance of tactile data, therefore, the key information can be acquired as much as possible when the number of tactile frames is limited. To handle the second problem, a multiple temporal scale 3D convolutional neural networks (MTS-3DCNNs) model is proposed, which downsamples the input tactile frames with multiple temporal scales (MTSs) and extracts the MTS deep features, and the fused features have better generalization capability for recognizing the object grasped with different speed. Furthermore, the existing lightweight network ResNet3D-18 is modified to obtain a MR3D-18 network which can match the tactile data with smaller size and prevent the overfitting problem. The ablation studies show the effectiveness of GAS strategy, MTS-3DCNNs, and MR3D-18 networks. The comprehensive comparisons with advanced methods demonstrate that our method is SOTA on two benchmarks.<\/jats:p>","DOI":"10.3389\/fnbot.2023.1159168","type":"journal-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T05:12:50Z","timestamp":1682485970000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Gradient adaptive sampling and multiple temporal scale 3D CNNs for tactile object recognition"],"prefix":"10.3389","volume":"17","author":[{"given":"Xiaoliang","family":"Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liying","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,4,26]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IJCNN52387.2021.9533388","article-title":"\u201cObject recognition for robotics from tactile time series data utilising different neural network architectures,\u201d","volume-title":"2021 International Joint Conference on Neural Networks (IJCNN)","author":"Bottcher","year":"2021"},{"key":"B2","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1145\/3517343.3517356","article-title":"\u201cTemporal and spatio-temporal domains for neuromorphic tactile texture classification,\u201d","volume-title":"Neuro-Inspired Computational Elements Conference","author":"Brayshaw","year":"2022"},{"key":"B3","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10412","article-title":"\u201cEfficient spatio-temporal tactile object recognition with randomized tiling convolutional networks in a hierarchical fusion strategy,\u201d","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Cao","year":"2016"},{"key":"B4","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1007\/s12559-018-9568-7","article-title":"End-to-end convnet for tactile recognition using residual orthogonal tiling and pyramid convolution ensemble","volume":"10","author":"Cao","year":"2018","journal-title":"Cogn. Comput."},{"key":"B5","first-page":"6299","article-title":"\u201cQuo vadis, action recognition? a new model and the kinetics dataset,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Carreira","year":"2017"},{"key":"B6","doi-asserted-by":"crossref","first-page":"9472","DOI":"10.1109\/IROS45743.2020.9341484","article-title":"\u201cVariable in-hand manipulations for tactile-driven robot hand via CNN-LSTM,\u201d","volume-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Funabashi","year":"2020"},{"key":"B7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICSENS.2017.8234203","article-title":"\u201cHuman and object recognition with a high-resolution tactile sensor,\u201d","volume-title":"2017 IEEE Sensors","author":"Gandarias","year":"2017"},{"key":"B8","first-page":"1","article-title":"\u201cA dynamic priority packet scheduling scheme for post-disaster UAV-assisted mobile ad hoc network,\u201d","volume-title":"2021 IEEE Wireless Communications and Networking Conference (WCNC)","author":"Gao","year":"2021"},{"key":"B9","first-page":"6546","article-title":"\u201cCan spatiotemporal 3D CNNs retrace the history of 2D CNNs and imagenet?\u201d","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition","author":"Hara","year":"2018"},{"key":"B10","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1007\/978-3-030-95498-7_39","article-title":"\u201cConvolutional neural networks based tactile object recognition for tactile sensing system,\u201d","volume-title":"Applications in Electronics Pervading Industry, Environment and Society: APPLEPIES 2021","author":"Ibrahim","year":"2022"},{"key":"B11","doi-asserted-by":"publisher","first-page":"8134","DOI":"10.1126\/scirobotics.abc8134","article-title":"Skin-inspired quadruple tactile sensors integrated on a robot hand enable object recognition","volume":"5","author":"Li","year":"2020","journal-title":"Sci. Robot."},{"key":"B12","unstructured":"LiY.\n            FanH.\n            QiuZ.\n            DouY.\n            XuL.\n            FangH.\n          Discovering a variety of objects in spatio-temporal human-object interactions. 2022"},{"key":"B13","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TCYB.2016.2614809","article-title":"Extreme kernel sparse learning for tactile object recognition","volume":"47","author":"Liu","year":"2016","journal-title":"IEEE Trans. Cybernet."},{"key":"B14","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.scib.2019.10.021","article-title":"Recent progress in tactile sensors and their applications in intelligent systems","volume":"65","author":"Liu","year":"2020","journal-title":"Sci. Bull."},{"key":"B15","doi-asserted-by":"publisher","first-page":"383","DOI":"10.3390\/jmse10030383","article-title":"An AUV target-tracking method combining imitation learning and deep reinforcement learning","volume":"10","author":"Mao","year":"2022","journal-title":"J. Marine Sci. Eng."},{"key":"B16","doi-asserted-by":"publisher","first-page":"5356","DOI":"10.3390\/s19245356","article-title":"Using 3D convolutional neural networks for tactile object recognition with robotic palpation","volume":"19","author":"Pastor","year":"2019","journal-title":"Sensors"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1177\/004051750407401207","article-title":"Tactile feeling: sensory analysis applied to textile goods","volume":"74","author":"Philippe","year":"2004","journal-title":"Textile Res. J."},{"key":"B18","doi-asserted-by":"publisher","first-page":"143","DOI":"10.3390\/rs12010143","article-title":"Object detection in remote sensing images based on improved bounding box regression and multi-level features fusion","volume":"12","author":"Qian","year":"2020","journal-title":"Remote Sens."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3167805","article-title":"Co-saliency detection guided by group weakly supervised learning","author":"Qian","year":"2022","journal-title":"IEEE Trans. Multimedia."},{"key":"B20","unstructured":"SharmaM.\n          Tactile-viewGCN: learning shape descriptor from tactile data using graph convolutional network. 2022"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1406","DOI":"10.3390\/jmse10101406","article-title":"Dynamic target tracking of autonomous underwater vehicle based on deep reinforcement learning","volume":"10","author":"Shi","year":"2022","journal-title":"J. Marine Sci. Eng."},{"key":"B22","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1109\/TOH.2014.2326159","article-title":"Incrementally learning objects by touch: online discriminative and generative models for tactile-based recognition","volume":"7","author":"Soh","year":"2014","journal-title":"IEEE Trans. Hapt."},{"key":"B23","doi-asserted-by":"crossref","first-page":"4489","DOI":"10.1109\/IROS.2012.6385992","article-title":"\u201cOnline spatio-temporal Gaussian process experts with application to tactile classification,\u201d","volume-title":"2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems","author":"Soh","year":"2012"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.3390\/mi13071053","article-title":"Contact pattern recognition of a flexible tactile sensor based on the CNN-LSTM fusion algorithm","volume":"13","author":"Song","year":"2022","journal-title":"Micromachines"},{"key":"B25","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1038\/s41528-022-00202-7","article-title":"An artificial neuromorphic somatosensory system with spatio-temporal tactile perception and feedback functions","volume":"6","author":"Sun","year":"2022","journal-title":"NPJ Flexible Electron."},{"key":"B26","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1038\/s41586-019-1234-z","article-title":"Learning the signatures of the human grasp using a scalable tactile glove","volume":"569","author":"Sundaram","year":"2019","journal-title":"Nature"},{"key":"B27","first-page":"1","article-title":"\u201cSmarthand: towards embedded smart hands for prosthetic and robotic applications,\u201d","volume-title":"2021 IEEE Sensors Applications Symposium (SAS)","author":"Wang","year":"2021"},{"key":"B28","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1126\/scirobotics.aat0429","article-title":"A skin-inspired tactile sensor for smart prosthetics","volume":"3","author":"Wu","year":"2018","journal-title":"Sci. Robot."},{"key":"B29","doi-asserted-by":"publisher","first-page":"2790","DOI":"10.1109\/TIE.2022.3170631","article-title":"Genetic algorithm-based ensemble hybrid sparse ELM for grasp stability recognition with multimodal tactile signals","volume":"70","author":"Yi","year":"2022","journal-title":"IEEE Trans. Indus. Electron."},{"key":"B30","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.3390\/e23111537","article-title":"Target classification method of tactile perception data with deep learning","volume":"23","author":"Zhang","year":"2021","journal-title":"Entropy"},{"key":"B31","unstructured":"ZhangY.\n            KanZ.\n            TseY. A.\n            YangY.\n            WangM. Y.\n          2018"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1159168\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T05:13:01Z","timestamp":1682485981000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1159168\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,26]]},"references-count":31,"alternative-id":["10.3389\/fnbot.2023.1159168"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1159168","relation":{},"ISSN":["1662-5218"],"issn-type":[{"type":"electronic","value":"1662-5218"}],"subject":[],"published":{"date-parts":[[2023,4,26]]},"article-number":"1159168"}}