{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T03:36:06Z","timestamp":1760240166881,"version":"build-2065373602"},"reference-count":23,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2019,3,14]],"date-time":"2019-03-14T00:00:00Z","timestamp":1552521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011381","name":"State Key Laboratory of Robotics and System","doi-asserted-by":"publisher","award":["SKLRS-2017-KF-06"],"award-info":[{"award-number":["SKLRS-2017-KF-06"]}],"id":[{"id":"10.13039\/501100011381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper is focused on designing a cost function of selecting a foothold for a physical quadruped robot walking on rough terrain. The quadruped robot is modeled with Denavit\u2013Hartenberg (DH) parameters, and then a default foothold is defined based on the model. Time of Flight (TOF) camera is used to perceive terrain information and construct a 2.5D elevation map, on which the terrain features are detected. The cost function is defined as the weighted sum of several elements including terrain features and some features on the relative pose between the default foothold and other candidates. It is nearly impossible to hand-code the weight vector of the function, so the weights are learned using Supporting Vector Machine (SVM) techniques, and the training data set is generated from the 2.5D elevation map of a real terrain under the guidance of experts. Four candidate footholds around the default foothold are randomly sampled, and the expert gives the order of such four candidates by rotating and scaling the view for seeing clearly. Lastly, the learned cost function is used to select a suitable foothold and drive the quadruped robot to walk autonomously across the rough terrain with wooden steps. Comparing to the approach with the original standard static gait, the proposed cost function shows better performance.<\/jats:p>","DOI":"10.3390\/s19061292","type":"journal-article","created":{"date-parts":[[2019,3,15]],"date-time":"2019-03-15T04:12:09Z","timestamp":1552623129000},"page":"1292","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Learning the Cost Function for Foothold Selection in a Quadruped Robot"],"prefix":"10.3390","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0057-9804","authenticated-orcid":false,"given":"Xingdong","family":"Li","sequence":"first","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hewei","family":"Gao","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fusheng","family":"Zha","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and System (HIT), Harbin 150080, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Li","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yangwei","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanling","family":"Guo","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2659-6677","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Academy of Aerospace Technology, Shenzhen 518057, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2019,3,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1007\/s10514-012-9321-0","article-title":"OctoMap: An efficient probabilistic 3D mapping framework based on octrees","volume":"34","author":"Hornung","year":"2013","journal-title":"Auton. Robots"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1177\/0278364906075165","article-title":"An efficient extension to elevation maps for outdoor terrain mapping and loop closing","volume":"26","author":"Pfaff","year":"2007","journal-title":"Int. J. Robot. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1515\/amcs-2016-0006","article-title":"RGB-D terrain perception and dense mapping for legged robots","volume":"26","author":"Belter","year":"2016","journal-title":"Int. J. Appl. Math. Comput. Sci."},{"key":"ref_4","first-page":"2231","article-title":"Estimating 6 DOF pose transformation of a TOF laser camera","volume":"44","author":"Xingdong","year":"2015","journal-title":"Infrared Laser Eng."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1023\/A:1008854305733","article-title":"Globally Consistent Range Scan Alignment for Environment Mapping","volume":"4","author":"Lu","year":"1997","journal-title":"Auton. Robots"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.robot.2007.07.002","article-title":"Globally consistent 3D mapping with scan matching","volume":"56","author":"Borrmann","year":"2008","journal-title":"Robot. Auton. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/j.isprsjprs.2018.01.003","article-title":"One-Two-One network for Compression Artifacts Reduction in Remote Sensing","volume":"145","author":"Zhang","year":"2018","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Wu, G., Han, J., Lin, Z., Ding, G., Zhang, B., and Ni, Q. (2018). Joint Image-Text Hashing for Fast Large-Scale Cross-Media Retrieval Using Self-Supervised Deep Learning. IEEE Trans. Ind. Electron., in press.","DOI":"10.1109\/TIE.2018.2873547"},{"key":"ref_9","unstructured":"Barasuol, V., Camurri, M., Bazeille, S., Caldwell, D.G., and Semini, C. (October, January 28). Reactive trotting with foot placement corrections through visual pattern classification. Proceedings of the IEEE International Conference on Intelligent Robots and Systems, Hamburg, Germany."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Fankhauser, P., Bjelonic, M., Bellicoso, C.D., Miki, T., and Hutter, M. (2018, January 21\u201325). Robust Rough-Terrain Locomotion with a Quadrupedal Robot. Proceedings of the IEEE International Conference on Robotics and Automation, Brisbane, QLD, Australia.","DOI":"10.1109\/ICRA.2018.8460731"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Mastalli, C., Havoutis, I., Winkler, A.W., Caldwell, D.G., and Semini, C. (2015, January 11\u201312). On-line and On-board Planning and Perception for Quadrupedal Locomotion. Proceedings of the IEEE Conference on Technologies for Practical Robot Applications (TEPRA), Boston, CA, USA.","DOI":"10.1109\/TePRA.2015.7219685"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"642","DOI":"10.1016\/j.neunet.2008.03.014","article-title":"Central Pattern Generators for Locomotion Control in Animals and Robots: A Review","volume":"21","author":"Ijspeert","year":"2008","journal-title":"Neural Netw."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Ajalooeian, M., Pouya, S., Sproewitz, A., and Ijspeert, A. (2013, January 6\u201310). Central Pattern Generators Augmented with Virtual Model Control for Quadruped Rough Terrain Locomotion. Proceedings of the IEEE International Conference on Robotics and Automation, Karlsruhe, Germany.","DOI":"10.1109\/ICRA.2013.6631040"},{"key":"ref_14","unstructured":"Peng, S., Lam, C., and Cole, G. (2003, January 14\u201319). A biologically inspired four legged walking robot. Proceedings of the IEEE International Conference on Robotics and Automation, Taipei, Taiwan."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1177\/0278364910388677","article-title":"Learning, Planning, and Control for Quadruped Locomotion over Challenging Terrain","volume":"30","author":"Kalakrishnan","year":"2011","journal-title":"Int. J. Robot. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1177\/0278364910390537","article-title":"The Stanford Littledog: A Learning and Rapid Replanning Approach to Quadruped Locomotion","volume":"30","author":"Kolter","year":"2011","journal-title":"Int. J. Robot. Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1177\/0278364910392608","article-title":"Optimization and Learning for Rough Terrain Legged Locomotion","volume":"30","author":"Zucker","year":"2011","journal-title":"Int. J. Robot. Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1177\/0278364910387681","article-title":"An Overview of the Defense Advanced Research Projects Agency\u2019s Learning Locomotion Program","volume":"30","author":"Pippine","year":"2011","journal-title":"Int. J. Robot. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1177\/0278364910387457","article-title":"The Littledog Robot","volume":"30","author":"Murphy","year":"2011","journal-title":"Int. J. Robot. Res."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kolter, J.Z., Kim, Y., and Ng, A.Y. (2009, January 12\u201317). Stereo Vision and Terrain Modeling for Quadruped Robots. Proceedings of the IEEE International Conference on Robotics and Automation, Kobe, Japan.","DOI":"10.1109\/ROBOT.2009.5152795"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Li, X., Li, J., and Guo, Y. (2017, January 27\u201331). Foothold selection for quadruped robot based on learning from expert. Proceedings of the IEEE International Conference on Advanced Robotics and Mechatronics, Hefei, China.","DOI":"10.1109\/ICARM.2017.8273164"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1002\/rob.20397","article-title":"Rough terrain mapping and classification for foothold selection in a walking robot","volume":"28","author":"Belter","year":"2011","journal-title":"J. Field Robot."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Mitchell, B., Hofmann, A.G., and Williams, B.C. (2007, January 10\u201314). Search-based Foot Placement for Quadrupedal Traversal of Challenging Terrain. Proceedings of the IEEE International Conference on Robotics and Automation, Roma, Italy.","DOI":"10.1109\/ROBOT.2007.363190"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/6\/1292\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:38:54Z","timestamp":1760186334000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/6\/1292"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3,14]]},"references-count":23,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2019,3]]}},"alternative-id":["s19061292"],"URL":"https:\/\/doi.org\/10.3390\/s19061292","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2019,3,14]]}}}