{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T02:55:43Z","timestamp":1790650543415,"version":"4.1.0"},"reference-count":35,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2017,2,8]],"date-time":"2017-02-08T00:00:00Z","timestamp":1486512000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Feed-forward model-based control relies on models of the controlled plant, e.g., in robotics on accurate knowledge of manipulator kinematics or dynamics. However, mechanical and analytical models do not capture all aspects of a plant\u2019s intrinsic properties and there remain unmodeled dynamics due to varying parameters, unmodeled friction or soft materials. In this context, machine learning is an alternative suitable technique to extract non-linear plant models from data. However, fully data-based models suffer from inaccuracies as well and are inefficient if they include learning of well known analytical models. This paper thus argues that feed-forward control based on hybrid models comprising an analytical model and a learned error model can significantly improve modeling accuracy. Hybrid modeling here serves the purpose to combine the best of the two modeling worlds. The hybrid modeling methodology is described and the approach is demonstrated for two typical problems in robotics, i.e., inverse kinematics control and computed torque control. The former is performed for a redundant soft robot and the latter for a rigid industrial robot with redundant degrees of freedom, where a complete analytical model is not available for any of the platforms.<\/jats:p>","DOI":"10.3390\/s17020311","type":"journal-article","created":{"date-parts":[[2017,2,10]],"date-time":"2017-02-10T05:27:09Z","timestamp":1486704429000},"page":"311","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["Hybrid Analytical and Data-Driven Modeling for Feed-Forward Robot Control \u2020"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3305-1157","authenticated-orcid":false,"given":"Ren\u00e9","family":"Reinhart","sequence":"first","affiliation":[{"name":"Fraunhofer Research Institute for Mechatronic Systems Design (IEM), Zukunftsmeile 1, 33102 Paderborn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeeshan","family":"Shareef","sequence":"additional","affiliation":[{"name":"Institute for Robotics and Process Control (IRP), Technische Universit\u00e4t Braunschweig, M\u00fchlenpfordstra\u00dfe 23, 38106 Braunschweig, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jochen","family":"Steil","sequence":"additional","affiliation":[{"name":"Institute for Robotics and Process Control (IRP), Technische Universit\u00e4t Braunschweig, M\u00fchlenpfordstra\u00dfe 23, 38106 Braunschweig, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2017,2,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Traversaro, S., Prete, A.D., Ivaldi, S., and Nori, F. (2015, January 26\u201330). Inertial parameters identification and joint torques estimation with proximal force\/torque sensing. Proceedings of the IEEE International Conference on Robotics and Automation, Seattle, WA, USA.","DOI":"10.1109\/ICRA.2015.7139476"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Vantilt, J., Aertbeli\u00ebn, E., Groote, F.D., and Schutter, J.D. (2015, January 26\u201330). Optimal Excitation and Identification of the Dynamic Model of Robotic Systems with Compliant Actuators. Proceedings of the IEEE International Conference on Robotics and Automation, Seattle, WA, USA.","DOI":"10.1109\/ICRA.2015.7139478"},{"key":"ref_3","unstructured":"Velthuis, W., de Vries, T., and van Amerongen, J. (1996, January 15\u201318). Learning feedforward control of a flexible beam. Proceedings of the IEEE International Symposium on Intelligent Control, Dearborn, MI, USA."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1023\/A:1015727715131","article-title":"Scalable Techniques from Nonparametric Statistics for Real Time Robot Learning","volume":"17","author":"Schaal","year":"2002","journal-title":"Appl. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Nguyen-Tuong, D., Seeger, M., and Peters, J. (2008, January 11\u201313). Computed torque control with nonparametric regression models. Proceedings of the American Control Conference, Seattle, WA, USA.","DOI":"10.1109\/ACC.2008.4586493"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1109\/TAMD.2010.2062511","article-title":"Goal Babbling Permits Direct Learning of Inverse Kinematics","volume":"2","author":"Rolf","year":"2010","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/TNNLS.2013.2287890","article-title":"Efficient Exploratory Learning of Inverse Kinematics on a Bionic Elephant Trunk","volume":"25","author":"Rolf","year":"2014","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.neunet.2010.08.011","article-title":"Bayesian robot system identification with input and output noise","volume":"24","author":"Ting","year":"2011","journal-title":"Neural Netw."},{"key":"ref_9","unstructured":"Nguyen-Tuong, D., Peters, J., Seeger, M., and Sch\u00f6lkopf, B. (2008, January 23\u201325). Learning Inverse Dynamics: A Comparison. Proceedings of the European Symposium on Artificial Neural Networks, Bruges, Belgium."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Nguyen-Tuong, D., and Peters, J. (2010, January 3\u20138). Using model knowledge for learning inverse dynamics. Proceedings of the IEEE International Conference on Robotics and Automation, Anchorage, AK, USA.","DOI":"10.1109\/ROBOT.2010.5509858"},{"key":"ref_11","unstructured":"Polydoros, A.S., Nalpantidis, L., and Kr\u00fcger, V. (October, January 28). Real-time deep learning of robotic manipulator Inverse Dynamics. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, Hamburg, Germany."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1016\/j.protcy.2016.08.060","article-title":"Design and Implementation of Intelligent Control Software for a Dough Kneader","volume":"26","author":"Oestersoetebier","year":"2016","journal-title":"Procedia Technol."},{"key":"ref_13","unstructured":"Um, T., Park, M.S., and Park, J.M. (June, January 31). Independent Joint Learning: A novel task-to-task transfer learning scheme for robot models. Proceedings of the IEEE International Conference on Robotics and Automation, Hong Kong, China."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Caluwaerts, K., and Steil, J.J. (2015, January 3\u20135). Independent Joint Learning in Practice: Local Error Estimates to Improve Inverse Dynamics Control. Proceedings of the IEEE-RAS International Conference on Humanoid Robots, Seoul, Korea.","DOI":"10.1109\/HUMANOIDS.2015.7363439"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.protcy.2016.08.003","article-title":"Hybrid Mechanical and Data-driven Modeling Improves Inverse Kinematic Control of a Soft Robot","volume":"26","author":"Reinhart","year":"2016","journal-title":"Procedia Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/j.ifacol.2016.10.653","article-title":"Improving the Inverse Dynamics Model of the KUKA LWR IV+ Using Independent Joint Learning","volume":"49","author":"Shareef","year":"2016","journal-title":"IFAC-PapersOnLine"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Shareef, Z., Reinhart, F., and Steil, J. (2016, January 9\u201314). Generalizing a learned inverse dynamic model of KUKA LWR IV+ for load variations using regression in the model space. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, Daejeon, Korea.","DOI":"10.1109\/IROS.2016.7759115"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Meier, F., Kappler, D., Ratliff, N., and Schaal, S. (2016, January 9\u201314). Towards robust online inverse dynamics learning. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, Daejeon, Korea.","DOI":"10.1109\/IROS.2016.7759594"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Rolf, M., and Steil, J. (2012, January 7\u201312). Constant curvature continuum kinematics as fast approximate model for the Bionic Handling Assistant. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, Vilamoura-Algarve, Portugal.","DOI":"10.1109\/IROS.2012.6385596"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1109\/TRO.2014.2314777","article-title":"A Variable Curvature Continuum Kinematics for Kinematic Control of the Bionic Handling Assistant","volume":"30","author":"Mahl","year":"2014","journal-title":"IEEE Trans. Robot."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Garofalo, G., Ott, C., and Albu-Sch\u00e4ffer, A. (2012, January 14\u201318). Walking control of fully actuated robots based on the bipedal slip model. Proceedings of the IEEE International Conference on Robotics and Automation, St Paul, MN, USA.","DOI":"10.1109\/ICRA.2012.6225272"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.neunet.2015.05.005","article-title":"Many regression algorithms, one unified model: A review","volume":"69","author":"Stulp","year":"2015","journal-title":"Neural Netw."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1142\/S021848851340014X","article-title":"Reliable Integration of Continuous Constraints into Extreme Learning Machines","volume":"21","author":"Neumann","year":"2013","journal-title":"Int. J. Uncertain. Fuzziness Knowl.-Based Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1108\/01445151111172907","article-title":"The Bionic Handling Assistant: A success story of additive manufacturing","volume":"31","author":"Grzesiak","year":"2011","journal-title":"Assem. Autom."},{"key":"ref_25","unstructured":"Bruno, D., Calinon, S., and Caldwell, D.G. (June, January 31). Null space redundancy learning for a flexible surgical robot. Proceedings of the IEEE International Conference on Robotics and Automation, Hong Kong, China."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"847","DOI":"10.1080\/01691864.2015.1037793","article-title":"A multi-level control architecture for the bionic handling assistant","volume":"29","author":"Rolf","year":"2015","journal-title":"Adv. Robot."},{"key":"ref_27","unstructured":"Spong, M., and Vidyasagar, M. (1989). Robot Dynamics and Control, John Wiley & Sons."},{"key":"ref_28","unstructured":"VICON Motion Tracking Systems. Available online: http:\/\/www.vicon.com."},{"key":"ref_29","unstructured":"Huang, G.B., Zhu, Q.Y., and Siew, C.K. (2004, January 25\u201329). Extreme learning machine: A new learning scheme of feedforward neural networks. Proceedings of the IEEE International Joint Conference on Neural Networks, Budapest, Hungary."},{"key":"ref_30","unstructured":"Schmidt, W., Kraaijveld, M., and Duin, R. (September, January 30). Feedforward neural networks with random weights. Proceedings of the IAPR International Conference on Pattern Recognition, Vol.II. Conference B: Pattern Recognition Methodology and Systems, The Hague, The Netherlands."},{"key":"ref_31","first-page":"321","article-title":"Multivariable Functional Interpolation and Adaptive Networks","volume":"2","author":"Broomhead","year":"1988","journal-title":"Compl. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1002\/rob.4620100505","article-title":"An efficient method for inverse dynamics of manipulators based on the virtual work principle","volume":"10","author":"Zhang","year":"1993","journal-title":"J. Robot. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Rohmer, E., Singh, S.P.N., and Freese, M. (2013, January 3\u20137). V-REP: A versatile and scalable robot simulation framework. Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, Tokyo, Japan.","DOI":"10.1109\/IROS.2013.6696520"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/100.486658","article-title":"A robotics toolbox for MATLAB","volume":"3","author":"Corke","year":"1996","journal-title":"IEEE Robot. Autom. Mag."},{"key":"ref_35","unstructured":"Gaz, C., Flacco, F., and Luca, A.D. (June, January 31). Identifying the Dynamic Model Used by the KUKA LWR: A Reverse Engineering Approach. Proceedings of the IEEE International Conference on Robotics and Automation, Hong Kong, China."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/2\/311\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:27:40Z","timestamp":1760207260000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/17\/2\/311"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,8]]},"references-count":35,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2017,2]]}},"alternative-id":["s17020311"],"URL":"https:\/\/doi.org\/10.3390\/s17020311","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2,8]]}}}