{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T06:31:55Z","timestamp":1773815515244,"version":"3.50.1"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Robot. AI"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Modern manufacturing demands flexible, robust robotic assembly systems capable of handling variable part geometries and dynamic task configurations. Current approaches often suffer from limited generalization, high sample complexity, and the need for extensive reconfiguration or retraining when task parameters change. This paper addresses these limitations by introducing a novel framework that enables adaptive reproduction of kinesthetically taught, contact-rich assembly policies, using only force\/torque and proprioceptive sensing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The approach combines three components: i. synchronized wrench\u2013motion Dynamic Movement Primitives (wDMPs) that encode coupled motion and wrench profiles from a single demonstration; ii. an uncertainty-aware Model Predictive Controller (MPC) that updates its model online to enable compliant and adaptive contact handling using uncertainty estimated via a Gaussian Mixture Model (GMM); and iii. a neural contact classifier based on Adaptive Resonance Theory (ART) that distinguishes intended contacts from unintended misalignments and coordinates transitions between assembly stages.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results and Discussion<\/jats:title>\n                    <jats:p>Trained on just two demonstrations, one kinesthetic teaching and one assisted successful reproduction, the framework was evaluated on standard benchmarks and real-world industrial scenarios, including peg-in-hole, plug insertion, and disc brake assemblies. Across 47 assemblies, our framework increased the success rate from 29.8% to 83% in comparison to a classic, nonadaptive compliant controller, and demonstrated improved robustness and transferability over baseline controllers under geometric and pose variations. This contributes towards enabling agile, customizable production with minimal reprogramming effort.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frobt.2026.1746577","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T05:37:30Z","timestamp":1773812250000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Fast reprogramming and adaptive reproduction of contact-rich assembly"],"prefix":"10.3389","volume":"13","author":[{"given":"Dimitrios","family":"Rakovitis","sequence":"first","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI GmbH), Robotics Innovation Center","place":["Bremen, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vamsi Krishna","family":"Origanti","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI GmbH), Robotics Innovation Center","place":["Bremen, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vinzenz","family":"Bargsten","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI GmbH), Robotics Innovation Center","place":["Bremen, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Danzglock","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI GmbH), Robotics Innovation Center","place":["Bremen, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dennis","family":"Mronga","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI GmbH), Robotics Innovation Center","place":["Bremen, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Frank","family":"Kirchner","sequence":"additional","affiliation":[{"name":"German Research Center for Artificial Intelligence (DFKI GmbH), Robotics Innovation Center","place":["Bremen, Germany"]},{"name":"Department of Mathematics and Informatics, University of Bremen","place":["Bremen, Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"104531","DOI":"10.1016\/j.robot.2023.104531","article-title":"Model-based variable impedance learning control for robotic manipulation","volume":"170","author":"Anand","year":"2023","journal-title":"Robotics Aut. Syst."},{"key":"B2","doi-asserted-by":"crossref","first-page":"4568","DOI":"10.1109\/IROS51168.2021.9635840","article-title":"Meta-learning for fast adaptive locomotion with uncertainties in environments and robot dynamics","volume-title":"2021 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","author":"Anne","year":"2021"},{"key":"B3","doi-asserted-by":"publisher","first-page":"3222","DOI":"10.1109\/LRA.2023.3264758","article-title":"Bayesian multi-task learning mpc for robotic mobile manipulation","volume":"8","author":"Arcari","year":"2023","journal-title":"IEEE Robotics Automation Lett."},{"key":"B4","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1007\/s11370-023-00481-7","article-title":"Actuator-level motion and contact episode learning and classification using adaptive resonance theory","volume":"16","author":"Bargsten","year":"2023","journal-title":"Intell. Serv. Robot."},{"key":"B5","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1007\/978-3-031-98304-7_39","article-title":"Continuous learning of contact episodes from proprioceptive sensors in industrial assembly scenarios using adaptive resonance theory","volume-title":"Intelligent and fuzzy systems","author":"Bargsten","year":"2025"},{"key":"B6","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1016\/j.automatica.2013.11.042","article-title":"Kullback\u2013leibler average, consensus on probability densities, and distributed state estimation with guaranteed stability","volume":"50","author":"Battistelli","year":"2014","journal-title":"Automatica"},{"key":"B7","doi-asserted-by":"crossref","first-page":"4702","DOI":"10.1109\/ICRA40945.2020.9196969","article-title":"Model predictive impedance control","volume-title":"2020 IEEE international conference on robotics and automation (ICRA)","author":"Bednarczyk","year":"2020"},{"key":"B8","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1109\/HUMANOIDS.2015.7363472","article-title":"Trac-ik: an open-source library for improved solving of generic inverse kinematics","volume-title":"2015 IEEE-RAS 15th international conference on humanoid robots (humanoids)","author":"Beeson","year":"2015"},{"key":"B9","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.neunet.2019.09.012","article-title":"A survey of adaptive resonance theory neural network models for engineering applications","volume":"120","author":"Brito da Silva","year":"2019","journal-title":"Neural Netw."},{"key":"B10","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1016\/j.neunet.2019.08.033","article-title":"Distributed dual vigilance fuzzy adaptive resonance theory learns online, retrieves arbitrarily-shaped clusters, and mitigates order dependence","volume":"121","author":"Brito da Silva","year":"2020","journal-title":"Neural Netw."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11370-015-0187-9","article-title":"A tutorial on task-parameterized movement learning and retrieval","volume":"9","author":"Calinon","year":"2016","journal-title":"Intell. Serv. Robot."},{"key":"B12","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1109\/TSMCB.2006.886952","article-title":"On learning, representing, and generalizing a task in a humanoid robot","volume":"37","author":"Calinon","year":"2007","journal-title":"IEEE Trans. Syst. Man, Cybern. Part B Cybern."},{"key":"B13","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/S0734-189X(87)80014-2","article-title":"A massively parallel architecture for a self-organizing neural pattern recognition machine","volume":"37","author":"Carpenter","year":"1987","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"B14","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1109\/IJCNN.1991.155368","article-title":"Fuzzy ART: an adaptive resonance algorithm for rapid, stable classification of analog patterns","volume-title":"IJCNN-91-Seattle international joint conference on neural networks","author":"Carpenter","year":"1991"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/SII.2019.8700380","article-title":"The pinocchio c++ library \u2013 a fast and flexible implementation of rigid body dynamics algorithms and their analytical derivatives","volume-title":"IEEE international symposium on system integrations (SII)","author":"Carpentier","year":"2019"},{"key":"B16","doi-asserted-by":"crossref","first-page":"1185","DOI":"10.1109\/AIM52237.2022.9863416","article-title":"Impedance adaptation by reinforcement learning with contact dynamic movement primitives","volume-title":"2022 IEEE\/ASME international conference on advanced intelligent mechatronics (AIM)","author":"Chang","year":"2022"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1825","DOI":"10.1080\/01691864.2012.685259","article-title":"Collision detection algorithm to distinguish between intended contact and unexpected collision","volume":"26","author":"Cho","year":"2012","journal-title":"Adv. Robot."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the em algorithm","volume":"39","author":"Dempster","year":"1977","journal-title":"J. R. Stat. Soc. Ser. B Methodol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"6695","DOI":"10.21105\/joss.06695","article-title":"Movement_primitives: imitation learning of cartesian motion with movement primitives","volume":"9","author":"Fabisch","year":"2024","journal-title":"J. Open Source Softw."},{"key":"B20","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1109\/TRO.2014.2304775","article-title":"Coupling movement primitives: interaction with the environment and bimanual tasks","volume":"30","author":"Gams","year":"2014","journal-title":"IEEE Trans. Robotics"},{"key":"B21","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.055","article-title":"Rvt-2: learning precise manipulation from few demonstrations","volume-title":"Proceedings of robotics: science and systems (delft, Netherlands)","author":"Goyal","year":"2024"},{"key":"B22","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/BF00340335","article-title":"Adaptive pattern classification and universal recoding: II. Feedback, expectation, olfaction, illusions","volume":"23","author":"Grossberg","year":"1976","journal-title":"Biol. Cybern."},{"key":"B23","article-title":"SRSA: skill retrieval and adaptation for robotic assembly tasks","volume-title":"Proceedings of the international conference on learning representations (ICLR)","author":"Guo","year":"2025"},{"key":"B24","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1080\/00401706.1970.10488634","article-title":"Ridge regression: biased estimation for nonorthogonal problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"B25","doi-asserted-by":"crossref","first-page":"2587","DOI":"10.1109\/ROBOT.2009.5152423","article-title":"Biologically-inspired dynamical systems for movement generation: automatic real-time goal adaptation and obstacle avoidance","volume-title":"2009 IEEE international conference on robotics and automation","author":"Hoffmann","year":"2009"},{"key":"B26","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1162\/NECO_a_00393","article-title":"Dynamical movement primitives: learning attractor models for motor behaviors","volume":"25","author":"Ijspeert","year":"2013","journal-title":"Neural Comput."},{"key":"B27","doi-asserted-by":"publisher","first-page":"eadn4008","DOI":"10.1126\/scirobotics.adn4008","article-title":"Intrinsic sense of touch for intuitive physical human-robot interaction","volume":"9","author":"Iskandar","year":"2024","journal-title":"Sci. Robotics"},{"key":"B28","doi-asserted-by":"publisher","first-page":"09543","DOI":"10.48550\/ARXIV.2206.09543","article-title":"Meta-learning for out-of-distribution detection via density estimation in latent space","author":"Iwata","year":"2022","journal-title":"Corr. Abs\/2206"},{"key":"B29","doi-asserted-by":"crossref","first-page":"1882","DOI":"10.23919\/ECC55457.2022.9838102","article-title":"Imitation and supervised learning of compliance for robotic assembly","volume-title":"2022 european control conference (ECC)","author":"Jha","year":"2022"},{"key":"B30","doi-asserted-by":"publisher","first-page":"101863","DOI":"10.1016\/j.rcim.2019.101863","article-title":"Reinforcement learning based on movement primitives for contact tasks","volume":"62","author":"Kim","year":"2020","journal-title":"Robotics Computer-Integrated Manuf."},{"key":"B31","doi-asserted-by":"crossref","first-page":"001951","DOI":"10.1109\/SMC.2016.7844525","article-title":"Contact distinction in human-robot cooperation with admittance control","volume-title":"2016 IEEE international conference on systems, man, and cybernetics (SMC)","author":"Kouris","year":"2016"},{"key":"B32","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1109\/LRA.2017.2789249","article-title":"A frequency domain approach for contact type distinction in human\u2013robot collaboration","volume":"3","author":"Kouris","year":"2018","journal-title":"IEEE Robotics Automation Lett."},{"key":"B33","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.robot.2017.09.019","article-title":"Generalization of orientation trajectories and force-torque profiles for robotic assembly","volume":"98","author":"Kramberger","year":"2017","journal-title":"Robotics Aut. Syst."},{"key":"B34","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/ICRA.2015.7138994","article-title":"Learning contact-rich manipulation skills with guided policy search","volume-title":"2015 IEEE international conference on robotics and automation (ICRA)","author":"Levine","year":"2015"},{"key":"B35","article-title":"Sonicsense: object perception from in-hand acoustic vibration","volume-title":"8th annual conference on robot learning","author":"Liu","year":"2024"},{"key":"B36","doi-asserted-by":"publisher","first-page":"021016","DOI":"10.1115\/1.4005789","article-title":"The costs of downtime incidents in serial multistage manufacturing systems","volume":"134","author":"Liu","year":"2012","journal-title":"J. Manuf. Sci. Eng."},{"key":"B37","doi-asserted-by":"crossref","first-page":"3080","DOI":"10.1109\/ICRA.2019.8793506","article-title":"Reinforcement learning on variable impedance controller for high-precision robotic assembly","volume-title":"2019 international conference on robotics and automation (ICRA)","author":"Luo","year":"2019"},{"key":"B38","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA40945.2020.9196673","article-title":"Crocoddyl: an efficient and versatile framework for multi-contact optimal control","volume-title":"IEEE international conference on robotics and automation (ICRA)","author":"Mastalli","year":"2020"},{"key":"B39","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1109\/ICRA48506.2021.9562066","article-title":"Model predictive robot-environment interaction control for mobile manipulation tasks","volume-title":"2021 IEEE international conference on robotics and automation (ICRA)","author":"Minniti","year":"2021"},{"key":"B40","doi-asserted-by":"crossref","first-page":"8010","DOI":"10.1109\/ICRA48891.2023.10161073","article-title":"Towards generalized robot assembly through compliance-enabled contact formations","volume-title":"2023 IEEE international conference on robotics and automation (ICRA)","author":"Morgan","year":"2023"},{"key":"B41","doi-asserted-by":"publisher","first-page":"4436","DOI":"10.1109\/LRA.2025.3551637","article-title":"Forge: force-guided exploration for robust contact-rich manipulation under uncertainty","volume":"10","author":"Noseworthy","year":"2025","journal-title":"IEEE Robotics Automation Lett."},{"key":"B42","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/978-3-030-97672-9_7","article-title":"Automatic parameterization of motion and force controlled robot skills","volume-title":"Robot intelligence technology and applications 6","author":"Origanti","year":"2022"},{"key":"B43","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1109\/SII59315.2025.10871056","article-title":"Look ahead optimization for managing nullspace in cartesian impedance control of dual-arm robots","volume-title":"2025 IEEE\/SICE international symposium on system integration (SII)","author":"Origanti","year":"2025"},{"key":"B44","doi-asserted-by":"crossref","first-page":"5087","DOI":"10.1109\/IROS55552.2023.10342219","article-title":"Learning contact-based state estimation for assembly tasks","volume-title":"2023 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","author":"Pankert","year":"2023"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.5555\/2999792.2999904","article-title":"Probabilistic movement primitives","volume":"26","author":"Paraschos","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B46","doi-asserted-by":"publisher","first-page":"6299","DOI":"10.1109\/TIE.2017.2682002","article-title":"Compliance-based robotic peg-in-hole assembly strategy without force feedback","volume":"64","author":"Park","year":"2017","journal-title":"IEEE Trans. Industrial Electron."},{"key":"B47","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1109\/ROBOT.2009.5152385","article-title":"Learning and generalization of motor skills by learning from demonstration","volume-title":"2009 IEEE international conference on robotics and automation (IEEE)","author":"Pastor","year":"2009"},{"key":"B48","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"B49","doi-asserted-by":"crossref","first-page":"1392","DOI":"10.1109\/ICRA57147.2024.10610115","article-title":"Gaussian mixture likelihood-based adaptive mpc for interactive mobile manipulators","volume-title":"2024 IEEE international conference on robotics and automation (ICRA)","author":"Rakovitis","year":"2024"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1109\/TRO.2023.3339543","article-title":"Active learning of discrete-time dynamics for uncertainty-aware model predictive control","volume":"40","author":"Saviolo","year":"2024","journal-title":"IEEE Trans. Robotics"},{"key":"B51","doi-asserted-by":"crossref","first-page":"9728","DOI":"10.1109\/IROS45743.2020.9340848","article-title":"Meta-reinforcement learning for robotic industrial insertion tasks","volume-title":"2020 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","author":"Schoettler","year":"2020"},{"key":"B52","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1109\/HUMANOIDS.2015.7363552","article-title":"Simultaneous kinesthetic teaching of positional and force requirements for sequential in-contact tasks","volume-title":"2015 IEEE-RAS 15th international conference on humanoid robots (humanoids)","author":"Steinmetz","year":"2015"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.039","article-title":"Industreal: transferring contact-rich assembly tasks from simulation to reality","author":"Tang","year":"2023","journal-title":"Robotics Sci. Syst"},{"key":"B54","doi-asserted-by":"crossref","first-page":"615","DOI":"10.23919\/ECC64448.2024.10591005","article-title":"On handling variable stiffness parameters in compliance control via mpc","volume-title":"2024 european control conference (ECC)","author":"Thelenberg","year":"2024"},{"key":"B55","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1109\/TRO.2010.2065430","article-title":"Task-specific generalization of discrete and periodic dynamic movement primitives","volume":"26","author":"Ude","year":"2010","journal-title":"IEEE Trans. Robotics"},{"key":"B56","doi-asserted-by":"crossref","first-page":"2997","DOI":"10.1109\/ICRA.2014.6907291","article-title":"Orientation in cartesian space dynamic movement primitives","volume-title":"2014 IEEE international conference on robotics and automation (ICRA)","author":"Ude","year":"2014"},{"key":"B57","doi-asserted-by":"crossref","first-page":"11831","DOI":"10.1109\/ICRA55743.2025.11127334","article-title":"Tacdiffusion: force-domain diffusion policy for precise tactile manipulation","volume-title":"2025 IEEE international conference on robotics and automation (ICRA)","author":"Wu","year":"2025"},{"key":"B58","first-page":"5960","article-title":"Real-time inertial parameter identification of floating-base robots through iterative primitive shape division","volume-title":"2022 international conference on robotics and automation (ICRA)","author":"Xu","year":""},{"key":"B59","first-page":"4649","article-title":"Learning efficient and robust multi-modal quadruped locomotion: a hierarchical approach","volume-title":"2022 international conference on robotics and automation (ICRA)","author":"Xu","year":""},{"key":"B60","doi-asserted-by":"crossref","first-page":"6003","DOI":"10.1109\/IROS51168.2021.9636147","article-title":"Learning-based contact status recognition for peg-in-hole assembly","volume-title":"2021 IEEE\/RSJ international conference on intelligent robots and systems (IROS)","author":"Yan","year":"2021"},{"key":"B61","article-title":"Deep autoencoding gaussian mixture model for unsupervised anomaly detection","volume-title":"International conference on learning representations","author":"Zong","year":"2018"}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1746577\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T05:37:36Z","timestamp":1773812256000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2026.1746577\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":61,"alternative-id":["10.3389\/frobt.2026.1746577"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2026.1746577","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]},"article-number":"1746577"}}