{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T10:01:12Z","timestamp":1777716072646,"version":"3.51.4"},"reference-count":48,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"publisher","award":["CHIST-ERA-17-ORMR-006"],"award-info":[{"award-number":["CHIST-ERA-17-ORMR-006"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The European Commission\u2019s Horizon 2020 Programme","award":["780684"],"award-info":[{"award-number":["780684"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The International Journal of Robotics Research"],"published-print":{"date-parts":[[2024,5]]},"abstract":"<jats:p>The convergence of many numerical optimization techniques is highly dependent on the initial guess given to the solver. To address this issue, we propose a novel approach that utilizes tensor methods to initialize existing optimization solvers near global optima. Our method does not require access to a database of good solutions. We first transform the cost function, which depends on both task parameters and optimization variables, into a probability density function. Unlike existing approaches, the joint probability distribution of the task parameters and optimization variables is approximated using the Tensor Train model, which enables efficient conditioning and sampling. We treat the task parameters as random variables, and for a given task, we generate samples for decision variables from the conditional distribution to initialize the optimization solver. Our method can produce multiple solutions (when they exist) faster than existing methods. We first evaluate the approach on benchmark functions for numerical optimization that are hard to solve using gradient-based optimization solvers with a naive initialization. The results show that the proposed method can generate samples close to global optima and from multiple modes. We then demonstrate the generality and relevance of our framework to robotics by applying it to inverse kinematics with obstacles and motion planning problems with a 7-DoF manipulator.<\/jats:p>","DOI":"10.1177\/02783649231217527","type":"journal-article","created":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T08:43:07Z","timestamp":1701333787000},"page":"811-839","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":7,"title":["Tensor train for global optimization problems in robotics"],"prefix":"10.1177","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7550-9368","authenticated-orcid":false,"given":"Suhan","family":"Shetty","sequence":"first","affiliation":[{"name":"Idiap Research Institute, Martigny, Switzerland"},{"name":"\u00c9cole Polytechnique Fed\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teguh","family":"Lembono","sequence":"additional","affiliation":[{"name":"Idiap Research Institute, Martigny, Switzerland"},{"name":"\u00c9cole Polytechnique Fed\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tobias","family":"L\u00f6w","sequence":"additional","affiliation":[{"name":"Idiap Research Institute, Martigny, Switzerland"},{"name":"\u00c9cole Polytechnique Fed\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9036-6799","authenticated-orcid":false,"given":"Sylvain","family":"Calinon","sequence":"additional","affiliation":[{"name":"Idiap Research Institute, Martigny, Switzerland"},{"name":"\u00c9cole Polytechnique Fed\u00e9rale de Lausanne (EPFL), Lausanne, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2023,11,30]]},"reference":[{"key":"bibr1-02783649231217527","first-page":"39","volume-title":"Mixture Models and Applications","author":"Calinon S","year":"2019"},{"key":"bibr2-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2297439"},{"key":"bibr3-02783649231217527","doi-asserted-by":"crossref","unstructured":"Dantec E, Budhiraja R, Roig A, et al. (2021) Whole body model predictive control with a memory of motion: experiments on a torque-controlled talos. In: Proceedings of IEEE international conference on robotics and automation (ICRA), Xi\u2019an, China, 30 May\u201305 June 2021, pp. 8202\u20138208.","DOI":"10.1109\/ICRA48506.2021.9560742"},{"key":"bibr4-02783649231217527","doi-asserted-by":"crossref","unstructured":"Deits R, Tedrake R (2014) Footstep planning on uneven terrain with mixed-integer convex optimization. In: Proceedings of IEEE-RAS international conference on humanoid robots, Madrid, Spain, 18\u201320 November 2014, pp. 279\u2013286.","DOI":"10.1109\/HUMANOIDS.2014.7041373"},{"key":"bibr5-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2019.106869"},{"key":"bibr6-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-019-09910-z"},{"key":"bibr7-02783649231217527","doi-asserted-by":"crossref","unstructured":"Escande A, Mansard N, Wieber PB (2010) Fast resolution of hierarchized inverse kinematics with inequality constraints. In: Proceedings IEEE international conference on robotics and automation, Anchorage, AK, USA, 03\u201307 May 2010, 3733\u20133738.","DOI":"10.1109\/ROBOT.2010.5509953"},{"key":"bibr8-02783649231217527","first-page":"247","author":"Goreinov SA","year":"2010","journal-title":"World Scientific"},{"key":"bibr9-02783649231217527","doi-asserted-by":"crossref","unstructured":"Gorodetsky A, Karaman S, Marzouk Y (2015) Efficient high-dimensional stochastic optimal motion control using tensor-train decomposition. In: Proceedings robotics: science and systems XI, Rome, Italy, July 2015, pp. 1\u20138.","DOI":"10.15607\/RSS.2015.XI.015"},{"key":"bibr10-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1002\/gamm.201310004"},{"key":"bibr11-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031012"},{"key":"bibr12-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"bibr13-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2623345"},{"key":"bibr14-02783649231217527","doi-asserted-by":"crossref","unstructured":"Horowitz MB, Damle A, Burdick JW (2014) Linear Hamilton Jacobi Bellman equations in high dimensions. In: Proceedings of IEEE conference on decision and control (CDC), Los Angeles, CA, USA, 15\u201317 December 2014, 5880\u20135887.","DOI":"10.1109\/CDC.2014.7040310"},{"key":"bibr15-02783649231217527","doi-asserted-by":"crossref","unstructured":"Jetchev N, Toussaint M (2009) Trajectory prediction: learning to map situations to robot trajectories. In: Proceedings of the 26th annual international conference on machine learning, ICML 2009, Montreal, Canada, 14\u201318 June 2009, pp. 449\u2013456.","DOI":"10.1145\/1553374.1553433"},{"key":"bibr16-02783649231217527","doi-asserted-by":"crossref","unstructured":"Kalakrishnan M, Chitta S, Theodorou E, et al. (2011) STOMP: stochastic trajectory optimization for motion planning. In: Proceedings of IEEE international conference on robotics and automation, Shanghai, China, 09\u201313 May 2011, pp. 4569\u20134574.","DOI":"10.1109\/ICRA.2011.5980280"},{"key":"bibr17-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1080\/03081087.2016.1267104"},{"key":"bibr18-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"bibr19-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1007\/s11045-017-0481-0"},{"key":"bibr20-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2972893"},{"key":"bibr21-02783649231217527","doi-asserted-by":"crossref","unstructured":"Mansard N, Del Prete A, Geisert M, et al. (2018) Using a memory of motion to efficiently warm-start a nonlinear predictive controller. In: Proceedings IEEE international conference on robotics and automation (ICRA), Brisbane, QLD, Australia, 21\u201325 May 2018, pp. 2986\u20132993.","DOI":"10.1109\/ICRA.2018.8463154"},{"key":"bibr22-02783649231217527","unstructured":"Miller J, Rabusseau G, Terilla J (2021) Tensor networks for probabilistic sequence modeling. In: Proceedings of international conference on artificial intelligence and statistics, pp. 3079\u20133087: PMLR."},{"key":"bibr23-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1177\/0278364918790369"},{"key":"bibr24-02783649231217527","unstructured":"Novikov G, Panov M, Oseledets I (2021) Tensor-train density estimation. In: Proceedings of the Thirty-Seventh Conference on Un- certainty in Artificial Intelligence volume 161. PMLR, pp. 1321\u20131331."},{"key":"bibr25-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920918296"},{"key":"bibr26-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211044405"},{"key":"bibr27-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1137\/090752286"},{"key":"bibr28-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2009.07.024"},{"key":"bibr29-02783649231217527","volume":"26","author":"Paraschos A","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bibr30-02783649231217527","doi-asserted-by":"crossref","unstructured":"Pignat E, Lembono T, Calinon S (2020) Variational inference with mixture model approximation for applications in robotics. In: Proceedings of IEEE international conference on robotics and automation (ICRA), Paris, France, 31 May\u201331 August 2020, pp. 3395\u20133401.","DOI":"10.1109\/ICRA40945.2020.9197166"},{"key":"bibr31-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211040561"},{"key":"bibr32-02783649231217527","unstructured":"Rabanser S, Shchur O, G\u00fcnnemann S (2017) Introduction to tensor decompositions and their applications in machine learning.\n                      ArXiv\n                      1711.10781."},{"key":"bibr33-02783649231217527","volume-title":"Gaussian Processes for Machine Learning","author":"Rasmussen C","year":"2006"},{"key":"bibr34-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1109\/101.17235"},{"key":"#cr-split#-bibr35-02783649231217527.1","doi-asserted-by":"crossref","unstructured":"Savostyanov DV, Oseledets IV (2011) Fast adaptive interpolation of multi-dimensional arrays in tensor train format. In: Proceedings of The 2011 international workshop on multidimensional","DOI":"10.1109\/nDS.2011.6076873"},{"key":"#cr-split#-bibr35-02783649231217527.2","unstructured":"(nD) systems, Poitiers, France, 05-07 September 2011, pp. 1-8."},{"key":"bibr36-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914528132"},{"key":"bibr37-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3087317"},{"key":"bibr38-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2690524"},{"key":"bibr39-02783649231217527","first-page":"26052","volume":"35","author":"Sozykin K","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bibr40-02783649231217527","doi-asserted-by":"publisher","DOI":"10.3390\/e21121236"},{"key":"bibr41-02783649231217527","doi-asserted-by":"crossref","unstructured":"Stolle M, Atkeson CG (2006) Policies based on trajectory libraries. In: Proceedings 2006 IEEE international conference on robotics and automation, 2006. ICRA 2006, Orlando, FL, USA, 15\u201319 May 2006, pp. 3344\u20133349.","DOI":"10.1109\/ROBOT.2006.1642212"},{"key":"bibr42-02783649231217527","doi-asserted-by":"crossref","unstructured":"Stolle M, Tappeiner H, Chestnutt J, et al. (2007) Transfer of policies based on trajectory libraries. In: Proceedings of IEEE\/RSJ international conference on intelligent robots and systems, San Diego, CA, USA, 10 December 2007, pp. 2981\u20132986.","DOI":"10.1109\/IROS.2007.4399364"},{"key":"bibr43-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2148230"},{"key":"bibr44-02783649231217527","doi-asserted-by":"crossref","unstructured":"Toussaint MA, Allen KR, Smith KA, et al. (2018) Differentiable physics and stable modes for tool-use and manipulation planning. In: Proceedings of robotics: science and systems 2018, Pittsburgh, PA, USA, 26\u201330 June 2018, pp. 1\u20138.","DOI":"10.15607\/RSS.2018.XIV.044"},{"key":"bibr45-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175354"},{"key":"bibr46-02783649231217527","first-page":"197","volume-title":"Large-Scale Scientific Computing","author":"Zheltkov DA","year":"2019"},{"key":"bibr47-02783649231217527","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913488805"}],"container-title":["The International Journal of Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231217527","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/02783649231217527","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/02783649231217527","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:17:16Z","timestamp":1777457836000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/02783649231217527"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":48,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2024,5]]}},"alternative-id":["10.1177\/02783649231217527"],"URL":"https:\/\/doi.org\/10.1177\/02783649231217527","relation":{},"ISSN":["0278-3649","1741-3176"],"issn-type":[{"value":"0278-3649","type":"print"},{"value":"1741-3176","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,30]]}}}