{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T09:20:04Z","timestamp":1787649604947,"version":"build-2736575974"},"reference-count":55,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004410","name":"Scientific and Technological Research Council of Turkey","doi-asserted-by":"publisher","award":["123E611"],"award-info":[{"award-number":["123E611"]}],"id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]},{"award":["123E611"],"award-info":[{"award-number":["123E611"]}],"id":[{"id":"https:\/\/ror.org\/04w9kkr77","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biomimetics"],"abstract":"<jats:p>Terrain types significantly affect the dynamics and locomotion performance of hexapod robots during walking. Terrain classification is a key solution to modify gait patterns in different terrains and recognize hazardous conditions. Perceiving the terrain with proprioceptive sensing is a robust and reliable approach in extreme conditions. In this paper, an efficient terrain classification approach for a hexapod robot is proposed. The proposed method combines a deep classification framework including the long short-term memory (LSTM) network and an effective statistical feature extraction. Proprioceptive inertial measurement unit (IMU) data is only used as the sensing system for the robot\u2013terrain interaction. In the feature extraction process, four meaningful characteristic features, namely, the mean, median, Lomb\u2013Scargle periodogram power spectral density (LPSD), and Welch\u2019s power spectral density (WPSD), are extracted from the body orientation data using a sliding-window method. These features are combined and fed into the network to perform the training and testing processes. In the experiments, the proposed method is evaluated with commonly used soft computing and deep learning models. The classification performance for the concrete, pebble, and waxed tile terrains reaches 100% with the proposed method. The overall accuracy, precision, sensitivity, specificity, F1-score, and Matthew correlation coefficient are recorded as 95.45%, 96.36%, 95.28%, 98.86%, 95.49%, and 94.61%, respectively. These results demonstrate that the proposed approach delivers reliable classification performance with a low-cost and easy-to-implement solution.<\/jats:p>","DOI":"10.3390\/biomimetics11090605","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T08:00:48Z","timestamp":1787644848000},"page":"605","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Proprioceptive Terrain Classification for Hexapod Robots with Statistical and Spectral Features"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5159-0659","authenticated-orcid":false,"given":"Deniz","family":"Korkmaz","sequence":"first","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Faculty of Engineering and Natural Sciences, Malatya Turgut Ozal University, Malatya 44900, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1750-8479","authenticated-orcid":false,"given":"Gonca","family":"Ozmen Koca","sequence":"additional","affiliation":[{"name":"Department of Mechatronics Engineering, Faculty of Technology, Firat University, Elazig 23119, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1199-2637","authenticated-orcid":false,"given":"Cafer","family":"Bal","sequence":"additional","affiliation":[{"name":"Department of Mechatronics Engineering, Faculty of Technology, Firat University, Elazig 23119, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9056-9975","authenticated-orcid":false,"given":"Mustafa","family":"Ay","sequence":"additional","affiliation":[{"name":"Department of Mechatronics Engineering, Faculty of Technology, Firat University, Elazig 23119, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7935-7031","authenticated-orcid":false,"given":"Zuhtu Hakan","family":"Akpolat","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, Faculty of Engineering, Fatih Sultan Mehmet Vakif University, Istanbul 34015, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"102644","DOI":"10.1016\/j.inffus.2024.102644","article-title":"Terrain detection and segmentation for autonomous vehicle navigation: A state-of-the-art systematic review","volume":"113","author":"Kabir","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"38507","DOI":"10.1109\/JSEN.2024.3472789","article-title":"Terrain Classification Based on Spatiotemporal Multihead Attention With Flexible Tactile Sensors Array","volume":"24","author":"Li","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_3","first-page":"100231","article-title":"Hierarchical reinforcement learning for enhancing stability and adaptability of hexapod robots in complex terrains","volume":"5","author":"Huang","year":"2025","journal-title":"Biomim. Intell. Robot."},{"key":"ref_4","first-page":"e00930","article-title":"Biomimetic soft-legged robotic locomotion, interactions and transitions in terrestrial, aquatic and multiple environments","volume":"40","author":"Yu","year":"2024","journal-title":"Sustain. Mater. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1080\/01691864.2024.2408619","article-title":"Decentralized control law for load-adaptive gaits of multi-legged robots inspired by millipedes","volume":"39","author":"Yasui","year":"2025","journal-title":"Adv. Robot."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"105731","DOI":"10.1016\/j.mechmachtheory.2024.105731","article-title":"Multiple terrain traversal capabilities based mechanism dimension design for a six-legged robot using performance charts from analytical conditions","volume":"201","author":"Xu","year":"2024","journal-title":"Mech. Mach. Theory"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"104917","DOI":"10.1016\/j.mechmachtheory.2022.104917","article-title":"Mechanism design and workspace analysis of a hexapod robot","volume":"174","author":"Li","year":"2022","journal-title":"Mech. Mach. Theory"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, J., Xue, Z., and Wu, Y. (2024). Research on stability of modular multi-legged robots with non-isomorphic configurations. Trans. Inst. Meas. Control.","DOI":"10.1177\/01423312241288043"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1109\/TRO.2019.2935336","article-title":"Tactile Sensing and Terrain-Based Gait Control for Small Legged Robots","volume":"36","author":"Wu","year":"2020","journal-title":"IEEE Trans. Robot."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1007\/s11370-023-00508-z","article-title":"Autonomous gait switching method and experiments of a hexapod walking robot for Mars environment with multiple terrains","volume":"17","author":"Chen","year":"2024","journal-title":"Intell. Serv. Robot."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5990","DOI":"10.1109\/LRA.2022.3160833","article-title":"Pressing and Rubbing: Physics-Informed Features Facilitate Haptic Terrain Classification for Legged Robots","volume":"7","author":"Ding","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"129328","DOI":"10.1016\/j.neucom.2024.129328","article-title":"Enhancing hexapod robot mobility on challenging terrains: Optimizing CPG-generated gait with reinforcement learning","volume":"622","author":"Huang","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1439","DOI":"10.1002\/rob.22463","article-title":"Development of a Load-Bearing, Terrain-Adaptive Hexapod Robot With Chebyshev-Linkage Legs","volume":"42","author":"Ju","year":"2024","journal-title":"J. F. Robot."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"156363","DOI":"10.1109\/ACCESS.2024.3485506","article-title":"Optimization Control of Attitude Stability for Hexapod Robots Based on Reinforcement Learning","volume":"12","author":"Ji","year":"2024","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"101028","DOI":"10.1016\/j.jterra.2024.101028","article-title":"Acoustic winter terrain classification for offroad autonomous vehicles","volume":"117","author":"Fragoso","year":"2025","journal-title":"J. Terramechanics"},{"key":"ref_16","first-page":"3567","article-title":"Feature-Temporal Semi-Supervised Extreme Learning Machine for Robotic Terrain Classification","volume":"67","author":"Lv","year":"2020","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3470","DOI":"10.1109\/LRA.2025.3541432","article-title":"See-Touch-Predict: Active Exploration and Online Perception of Terrain Physics With Legged Robots","volume":"10","author":"Lin","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"126862","DOI":"10.1016\/j.eswa.2025.126862","article-title":"A multi-modal sensing based terrain identification approach for active lower limb exoskeletons","volume":"275","author":"Das","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"3150","DOI":"10.1109\/LRA.2025.3541428","article-title":"Online Friction Coefficient Identification for Legged Robots on Slippery Terrain Using Smoothed Contact Gradients","volume":"10","author":"Kim","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"7190","DOI":"10.1109\/LRA.2024.3418270","article-title":"ProNav: Proprioceptive Traversability Estimation for Legged Robot Navigation in Outdoor Environments","volume":"9","author":"Elnoor","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Santo, A., Heredia, E., Viegas, C., Valiente, D., and Gil, A. (2025). Ground Segmentation for LiDAR Point Clouds in Structured and Unstructured Environments Using a Hybrid Neural\u2013Geometric Approach. Technologies, 13.","DOI":"10.3390\/technologies13040162"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"127495","DOI":"10.1016\/j.eswa.2025.127495","article-title":"Terrain classification method based on fusion of vision and vehicle dynamics for UGV","volume":"279","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huang, B., Hong, M., Huang, C., Wang, G., and Guo, M. (2025). A Terrain Classification Method for Quadruped Robots with Proprioception. Electronics, 14.","DOI":"10.3390\/electronics14061231"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/s11063-024-11679-w","article-title":"A Robot Ground Medium Classification Algorithm Based on Feature Fusion and Adaptive Spatio-Temporal Cascade Networks","volume":"56","author":"Feng","year":"2024","journal-title":"Neural Process. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"109539","DOI":"10.1016\/j.compag.2024.109539","article-title":"Terrain classification method using an NIR or RGB camera with a CNN-based fusion of vision and a reduced-order proprioception model","volume":"227","author":"Chen","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jterra.2022.11.003","article-title":"Off-road terrain classification","volume":"106","author":"Fritz","year":"2023","journal-title":"J. Terramechanics"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"110319","DOI":"10.1016\/j.measurement.2021.110319","article-title":"A road level identification method for all-terrain crane based on Support Vector Machine","volume":"187","author":"Wang","year":"2022","journal-title":"Measurement"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"104339","DOI":"10.1016\/j.robot.2022.104339","article-title":"Efficient surface detection for assisting Collaborative Robots","volume":"161","author":"Singh","year":"2023","journal-title":"Rob. Auton. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"112761","DOI":"10.1016\/j.knosys.2024.112761","article-title":"A lightweight convolutional neural network for road surface classification under shadow interference","volume":"306","author":"Mao","year":"2024","journal-title":"Knowl.-Based Syst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"101022","DOI":"10.1016\/j.jterra.2024.101022","article-title":"Terrain classification and rock abundance analysis at Utopia Planitia using Zhurong image data based on deep learning algorithms","volume":"117","author":"Shen","year":"2025","journal-title":"J. Terramechanics"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"4644","DOI":"10.1109\/LRA.2025.3552997","article-title":"An Online System Identification Algorithm for Spherical Robot Using the Koopman Theory","volume":"10","author":"Guan","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_32","first-page":"1","article-title":"An Adaptive Across Time\u2013Space-Domain Perception Method for Rescue Robots Based on DN-CycleGAN and MR-Xception Transfer Learning","volume":"74","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"9218","DOI":"10.1109\/TASE.2024.3503277","article-title":"TFGait\u2014Stable and Efficient Adaptive Gait Planning With Terrain Recognition and Froude Number for Quadruped Robot","volume":"22","author":"Luo","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"6720","DOI":"10.1109\/LRA.2024.3408084","article-title":"Foot Vision: A Vision-Based Multi-Functional Sensorized Foot for Quadruped Robots","volume":"9","author":"Shi","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Jia, C., Ma, C., and Liu, Q. (2019). SURF-BRISK-based image infilling method for terrain classification of a legged robot. Appl. Sci., 9.","DOI":"10.3390\/app9091779"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"23308","DOI":"10.1109\/JSEN.2021.3109864","article-title":"Terrain Classification Based on Sensed Leg Compliance for Amphibious Crab Robot","volume":"21","author":"Grezmak","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lokhande, S., Bao, Y., Cheng, P., Shen, D., Chen, G., and Xu, H. (2025). Real-Time Proprioceptive Sensing Enhanced Switching Model Predictive Control for Quadruped Robot Under Uncertain Environment. Electronics, 14.","DOI":"10.3390\/electronics14132681"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"104512","DOI":"10.1016\/j.robot.2023.104512","article-title":"Real-time terrain anomaly perception for safe robot locomotion using a digital double framework","volume":"169","author":"Haddeler","year":"2023","journal-title":"Rob. Auton. Syst."},{"key":"ref_39","first-page":"100091","article-title":"An online terrain classification framework for legged robots based on acoustic signals","volume":"3","author":"Qin","year":"2023","journal-title":"Biomim. Intell. Robot."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.cogr.2025.04.002","article-title":"Robotic terrain classification based on convolutional and long short-term memory neural networks","volume":"5","author":"Hu","year":"2025","journal-title":"Cogn. Robot."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"110904","DOI":"10.1016\/j.measurement.2022.110904","article-title":"Accurate perception and representation of rough terrain for a hexapod robot by analysing foot locomotion","volume":"193","author":"Li","year":"2022","journal-title":"Meas. J. Int. Meas. Confed."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"6821","DOI":"10.1109\/TMECH.2025.3528031","article-title":"Terrain Perception and Stiffness Adaptation-Based Attitude Control for Quadruped Robots","volume":"30","author":"Huang","year":"2025","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"365","DOI":"10.34133\/cbsystems.0365","article-title":"Bridging the Gap to Bionic Motion: Challenges in Legged Robot Limb Unit Design, Modeling, and Control","volume":"6","author":"Zhang","year":"2025","journal-title":"Cyborg Bionic Syst."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.neucom.2020.07.114","article-title":"Neural coupled central pattern generator based smooth gait transition of a biomimetic hexapod robot","volume":"420","author":"Bal","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s10846-023-02047-2","article-title":"CPG-Fuzzy Heading Control for a Hexapod Robot with Arc-Shaped Blade Legs","volume":"110","author":"Zhang","year":"2024","journal-title":"J. Intell. Robot. Syst."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"102068","DOI":"10.1016\/j.jksuci.2024.102068","article-title":"RNN-LSTM: From applications to modeling techniques and beyond\u2014Systematic review","volume":"36","author":"Hassan","year":"2024","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"127728","DOI":"10.1016\/j.eswa.2025.127728","article-title":"Bootstrap prediction intervals for the long short term memory (LSTM) recurrent neural network","volume":"284","author":"Rockefeller","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"144","DOI":"10.30941\/CESTEMS.2023.00014","article-title":"Fault Detection for Motor Drive Control System of Industrial Robots Using CNN-LSTM-based Observers","volume":"7","author":"Wang","year":"2023","journal-title":"CES Trans. Electr. Mach. Syst."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"110074","DOI":"10.1016\/j.cie.2024.110074","article-title":"Multimodal 1D CNN for delamination prediction in CFRP drilling process with industrial robots","volume":"190","author":"Choi","year":"2024","journal-title":"Comput. Ind. Eng."},{"key":"ref_50","first-page":"281","article-title":"Median-mean line based collaborative representation for PolSAR terrain classification","volume":"25","author":"Imani","year":"2022","journal-title":"Egypt. J. Remote Sens. Sp. Sci."},{"key":"ref_51","first-page":"1","article-title":"REPESgram: A Novel Method for the Optimal Demodulation Band Selection in Rolling Bearing Fault Diagnosis","volume":"74","author":"Wang","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"116604","DOI":"10.1016\/j.oceaneng.2023.116604","article-title":"Deep-learning approach based on multi-data fusion for damage recognition of marine platforms under complex loads","volume":"303","author":"Xin","year":"2024","journal-title":"Ocean Eng."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"113105","DOI":"10.1016\/j.measurement.2023.113105","article-title":"Generalizable end-to-end deep learning frameworks for real-time attitude estimation using 6DoF inertial measurement units","volume":"217","author":"Sabour","year":"2023","journal-title":"Measurement"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1007\/s11465-020-0623-1","article-title":"Terrain classification and adaptive locomotion for a hexapod robot Qingzhui","volume":"16","author":"Zhao","year":"2021","journal-title":"Front. Mech. Eng."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"1848","DOI":"10.1109\/LRA.2021.3060437","article-title":"Semi-Supervised Gated Recurrent Neural Networks for Robotic Terrain Classification","volume":"6","author":"Ahmadi","year":"2021","journal-title":"IEEE Robot. Autom. Lett."}],"container-title":["Biomimetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/9\/605\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T08:31:48Z","timestamp":1787646708000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-7673\/11\/9\/605"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":55,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["biomimetics11090605"],"URL":"https:\/\/doi.org\/10.3390\/biomimetics11090605","relation":{},"ISSN":["2313-7673"],"issn-type":[{"value":"2313-7673","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]}}}