{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:10:24Z","timestamp":1760137824250,"version":"build-2065373602"},"reference-count":18,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T00:00:00Z","timestamp":1649808000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Improving the capabilities of optimization-based motion planning and control algorithms","award":["PSG605"],"award-info":[{"award-number":["PSG605"]}]},{"name":"Autonomous mobile robot park for hospital management during COVID-19","award":["COVSG24"],"award-info":[{"award-number":["COVSG24"]}]},{"name":"Implementation of the research support measure of the IT Academy (4) COOPERATION ROOTICS","award":["SLTTI19605T"],"award-info":[{"award-number":["SLTTI19605T"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Joint space trajectory optimization under end-effector task constraints leads to a challenging non-convex problem. Thus, a real-time adaptation of prior computed trajectories to perturbation in task constraints often becomes intractable. Existing works use the so-called warm-starting of trajectory optimization to improve computational performance. We present a fundamentally different approach that relies on deriving analytical gradients of the optimal solution with respect to the task constraint parameters. This gradient map characterizes the direction in which the prior computed joint trajectories need to be deformed to comply with the new task constraints. Subsequently, we develop an iterative line-search algorithm for computing the scale of deformation. Our algorithm provides near real-time adaptation of joint trajectories for a diverse class of task perturbations, such as (i) changes in initial and final joint configurations of end-effector orientation-constrained trajectories and (ii) changes in end-effector goal or way-points under end-effector orientation constraints. We relate each of these examples to real-world applications ranging from learning from demonstration to obstacle avoidance. We also show that our algorithm produces trajectories with quality similar to what one would obtain by solving the trajectory optimization from scratch with warm-start initialization. Most importantly, however, our algorithm achieves a worst-case speed-up of 160x over the latter approach.<\/jats:p>","DOI":"10.3390\/s22082995","type":"journal-article","created":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T23:07:16Z","timestamp":1649891236000},"page":"2995","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Fast Adaptation of Manipulator Trajectories to Task Perturbation by Differentiating through the Optimal Solution"],"prefix":"10.3390","volume":"22","author":[{"given":"Shashank","family":"Srikanth","sequence":"first","affiliation":[{"name":"Robotics Research Center, KCIS, IIIT Hyderabad, Hyderabad 500032, India"}]},{"given":"Mithun","family":"Babu","sequence":"additional","affiliation":[{"name":"Robotics Research Center, KCIS, IIIT Hyderabad, Hyderabad 500032, India"}]},{"given":"Houman","family":"Masnavi","sequence":"additional","affiliation":[{"name":"Institute of Technology, University of Tartu, 50090 Tartu, Estonia"}]},{"given":"Arun","family":"Kumar Singh","sequence":"additional","affiliation":[{"name":"Institute of Technology, University of Tartu, 50090 Tartu, Estonia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1720-1509","authenticated-orcid":false,"given":"Karl","family":"Kruusam\u00e4e","sequence":"additional","affiliation":[{"name":"Institute of Technology, University of Tartu, 50090 Tartu, Estonia"}]},{"given":"Krishnan Madhava","family":"Krishna","sequence":"additional","affiliation":[{"name":"Robotics Research Center, KCIS, IIIT Hyderabad, Hyderabad 500032, India"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Berenson, D., Srinivasa, S.S., Ferguson, D., and Kuffner, J.J. (2009, January 12\u201317). Manipulation planning on constraint manifolds. Proceedings of the 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan.","DOI":"10.1109\/ROBOT.2009.5152399"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2594","DOI":"10.1109\/LRA.2020.2972893","article-title":"Memory of motion for warm-starting trajectory optimization","volume":"5","author":"Lembono","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"ref_4","unstructured":"Gould, S., Fernando, B., Cherian, A., Anderson, P., Cruz, R.S., and Guo, E. (2016). On differentiating parameterized argmin and argmax problems with application to bi-level optimization. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/TRO.2016.2623345","article-title":"Learning the problem-optimum map: Analysis and application to global optimization in robotics","volume":"33","author":"Hauser","year":"2016","journal-title":"IEEE Trans. Robot."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Tang, G., Sun, W., and Hauser, K. (2019, January 3\u20138). Time-Optimal Trajectory Generation for Dynamic Vehicles: A Bilevel Optimization Approach. Proceedings of the 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China.","DOI":"10.1109\/IROS40897.2019.8968104"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Reiter, A., Gattringer, H., and M\u00fcller, A. (2017, January 21\u201323). Real-time computation of inexact minimum-energy trajectories using parametric sensitivities. Proceedings of the International Conference on Robotics in Alpe-Adria Danube Region, Torino, Italy.","DOI":"10.1007\/978-3-319-61276-8_20"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1080\/10556788.2016.1200045","article-title":"Feasibility refinement in sequential quadratic programming using parametric sensitivity analysis","volume":"32","author":"Geffken","year":"2017","journal-title":"Optim. Methods Softw."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1007\/s12532-012-0043-2","article-title":"Optimal sensitivity based on IPOPT","volume":"4","author":"Pirnay","year":"2012","journal-title":"Math. Program. Comput."},{"key":"ref_10","unstructured":"Amos, B., Jimenez, I., Sacks, J., Boots, B., and Kolter, J.Z. (2018). Differentiable MPC for end-to-end planning and control. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_11","unstructured":"Agrawal, A., Barratt, S., Boyd, S., and Stellato, B. (2020, January 11\u201312). Learning convex optimization control policies. Proceedings of the 2nd Conference on Learning for Dynamics and Control, PMLR, Berkeley, CA, USA."},{"key":"ref_12","unstructured":"Landry, B., Lorenzetti, J., Manchester, Z., and Pavone, M. (2019). Bilevel Optimization for Planning through Contact: A Semidirect Method. arXiv."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1049\/iet-cta.2019.0556","article-title":"Fast l1 model predictive control based on sensitivity analysis strategy","volume":"14","author":"Kalantari","year":"2020","journal-title":"IET Control. Theory Appl."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1533","DOI":"10.1109\/TRO.2014.2351113","article-title":"A general, fast, and robust implementation of the time-optimal path parameterization algorithm","volume":"30","author":"Pham","year":"2014","journal-title":"IEEE Trans. Robot."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Toussaint, M. (2017). A tutorial on Newton methods for constrained trajectory optimization and relations to SLAM, Gaussian Process smoothing, optimal control, and probabilistic inference. Geometric and Numerical Foundations of Movements, Springer.","DOI":"10.1007\/978-3-319-51547-2_15"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Flacco, F., Kr\u00f6ger, T., De Luca, A., and Khatib, O. (2012, January 11\u201314). A depth space approach to human-robot collision avoidance. Proceedings of the 2012 IEEE International Conference on Robotics and Automation, Guangzhou, China.","DOI":"10.1109\/ICRA.2012.6225245"},{"key":"ref_17","unstructured":"Bradbury, J., Frostig, R., Hawkins, P., Johnson, M.J., Leary, C., Maclaurin, D., and Wanderman-Milne, S. (2020, August 01). JAX: Composable Transformations of Python+NumPy Programs. Available online: http:\/\/github.com\/google\/jax."},{"key":"ref_18","unstructured":"Qureshi, A.H., Dong, J., Baig, A., and Yip, M.C. (2020). Constrained Motion Planning Networks X. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/8\/2995\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:53:32Z","timestamp":1760136812000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/8\/2995"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,13]]},"references-count":18,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["s22082995"],"URL":"https:\/\/doi.org\/10.3390\/s22082995","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,4,13]]}}}