{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T14:33:16Z","timestamp":1776436396139,"version":"3.51.2"},"reference-count":36,"publisher":"Walter de Gruyter GmbH","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,1,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper introduces a benchmark framework to evaluate the performance of reaching motion generation approaches that learn from demonstrated examples. The system implements ten different performance measures for typical generalization tasks in robotics using open source MATLAB software. Systematic comparisons are based on a default training data set of human motions, which specify the respective ground truth. In technical terms, an evaluated motion generation method needs to compute velocities, given a state provided by the simulation system. This however is agnostic to how this is done by the method or how the methods learns from the provided demonstrations. The framework focuses on robustness, which is tested statistically by sampling from a set of perturbation scenarios. These perturbations interfere with motion generation and challenge its generalization ability. The benchmark thus helps to identify the strengths and weaknesses of competing approaches, while allowing the user the opportunity to configure the weightings between different measures.<\/jats:p>","DOI":"10.1515\/pjbr-2015-0002","type":"journal-article","created":{"date-parts":[[2015,4,20]],"date-time":"2015-04-20T13:45:51Z","timestamp":1429537551000},"source":"Crossref","is-referenced-by-count":19,"title":["Open-source benchmarking for learned reaching motion generation in robotics"],"prefix":"10.1515","volume":"6","author":[{"given":"A.","family":"Lemme","sequence":"first","affiliation":[]},{"given":"Y.","family":"Meirovitch","sequence":"additional","affiliation":[]},{"given":"M.","family":"Khansari-Zadeh","sequence":"additional","affiliation":[]},{"given":"T.","family":"Flash","sequence":"additional","affiliation":[]},{"given":"A.","family":"Billard","sequence":"additional","affiliation":[]},{"given":"J. J.","family":"Steil","sequence":"additional","affiliation":[]}],"member":"374","reference":[{"key":"ref411","first-page":"105","article-title":"Human arm trajectory formation","author":"Abend","year":"1982","journal-title":"Exp Brain Res"},{"key":"ref141","first-page":"1216","article-title":"Neural learning of stable dynamical systems based on data - driven Lyapunov candidates In Proc of Int Intelligent Robots and Systems pages","author":"Neumann","year":"2013","journal-title":"IEEE"},{"key":"ref191","first-page":"54","article-title":"The law relating kinematic and figural aspects of drawing movements","author":"Lacquaniti","year":"1983","journal-title":"Acta Psychologica"},{"key":"ref461","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1016\/j.conb.2005.10.011","article-title":"Motor primitives in vertebrates and invertebrates Current in Motor sytems Neurobiology of behaviour","volume":"15","author":"Flash","year":"2005","journal-title":"Opinion Neurobiology"},{"key":"ref211","doi-asserted-by":"crossref","first-page":"2745","DOI":"10.1523\/JNEUROSCI.04-11-02745.1984","article-title":"An organizing principle for a class of voluntary movements","volume":"4","author":"Hogan","year":"1984","journal-title":"Journal of Neuroscience"},{"key":"ref231","first-page":"80","article-title":"Smoothness maximization along a predefined path accurately predicts the speed profiles of complex arm movements","author":"Todorov","year":"1998","journal-title":"Neurophysiol"},{"key":"ref501","article-title":"Workshop on benchmarking of state - of - the - art algorithms in generating human - like robot reaching motions In Humanoids","author":"Khansari","year":"2013","journal-title":"IEEE"},{"key":"ref471","doi-asserted-by":"crossref","first-page":"3932","DOI":"10.1523\/JNEUROSCI.17-10-03932.1997","article-title":"The relationsheep between curvature and velocity in two dimensional smooth pursuit eye movement The","volume":"17","author":"Viviani","year":"1997","journal-title":"Journal of Neuroscience"},{"key":"ref81","first-page":"264","article-title":"Fair and comprehensive methodology for comparing hardware performance of fourteen round two SHA - candidates using FPGAs In Cryptographic Hardware and Embedded Systems pages","author":"Gaj","year":"2010","journal-title":"CHES"},{"key":"ref301","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1016\/j.robot.2014.03.001","article-title":"Learning control lyapunov function to ensure stability of dynamical system - based robot reaching motions robotics and autonomous systems Robotics and","volume":"62","author":"Khansari","year":"2014","journal-title":"Autonomous Systems"},{"key":"ref311","first-page":"1305","article-title":"Kinesthetic teaching via fast marching square In Proc of Int on Intelligent Robots and Systems pages","author":"G\u00f3mez","year":"2012","journal-title":"IEEE"},{"key":"ref491","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/s00422-008-0287-0","article-title":"Parabolic movement primitives and cortical states : merging optimality with geometric invariance","volume":"100","author":"Polyakov","year":"2009","journal-title":"Biological Cybernetics"},{"key":"ref171","first-page":"763","article-title":"Learning and generalization of motor skills by learning from demonstration In Proc of Int on Robotics and Automation pages","author":"Pastor","year":"2009","journal-title":"IEEE"},{"key":"ref221","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1523\/JNEUROSCI.05-07-01688.1985","article-title":"The coordination of arm movements - an experimentally confirmed mathematical - model","volume":"5","author":"Flash","year":"1985","journal-title":"Journal of Neuroscience"},{"key":"ref131","first-page":"141","article-title":"Neural learning of vector fields for encoding stable dynamical systems","author":"Lemme","year":"2014","journal-title":"Neurocomputing"},{"key":"ref321","doi-asserted-by":"crossref","first-page":"3208","DOI":"10.1523\/JNEUROSCI.14-05-03208.1994","article-title":"Adaptive representation of dynamics during learning of a motor task","volume":"14","author":"Shadmehr","year":"1994","journal-title":"Neuroscience"},{"key":"ref31","first-page":"96","article-title":"Motor interference between humans and humanoid robots : Effect of biological and artificial motion In Proc of Int on Development and Learning pages","author":"Chaminade","year":"2005","journal-title":"IEEE"},{"key":"ref61","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.robot.2008.10.024","article-title":"Manuela and Brett Browning A survey of robot learning from demonstration Robotics and","volume":"57","author":"Brenna","year":"2009","journal-title":"Autonomous Systems"},{"key":"ref371","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1016\/j.cortex.2008.03.010","article-title":"Three - dimensional arm movements at constant equiaflne speed","volume":"45","author":"Pollick","year":"2009","journal-title":"Cortex"},{"key":"ref91","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1007\/s101070100263","article-title":"Benchmarking optimization software with performance profiles","volume":"91","author":"Dolan","year":"2002","journal-title":"Mathematical programming"},{"key":"ref11","first-page":"376","article-title":"Ch and Gerd Hirzinger The dlr lightweight robot : design and control concepts for robots in human environments Industrial Robot : An","volume":"34","author":"Alin","year":"2007","journal-title":"International Journal"},{"key":"ref441","first-page":"355","article-title":"Ivaladi Motor learning through the combination of primitives Philosophical Transactions of the -","author":"Bizzi","year":"2000","journal-title":"Royal Society of London Series B Biological Sciences"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.robot.2004.03.004","article-title":"Christopher Programming full - body movements for humanoid robots by observation Robotics and","volume":"47","author":"Ale\u0161 Ude","year":"2004","journal-title":"Autonomous Systems"},{"key":"ref01","first-page":"25","article-title":"Humanoid robots : a new kind of tool IEEE Intell Control","volume":"15","author":"Adams","year":"2000","journal-title":"Syst lett"},{"key":"ref511","doi-asserted-by":"crossref","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 computation"},{"key":"ref351","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1007\/s00221-002-1054-4","article-title":"Does the motor control system use multiple models and context switching to cope with a variable environment","volume":"143","author":"Karniel","year":"2002","journal-title":"Experimental Brain Research"},{"key":"ref431","first-page":"394","article-title":"Signal - dependent noise determines motor planning","author":"Harris","year":"1998","journal-title":"Nature"},{"key":"ref111","first-page":"610","article-title":"On improving the extrapolation capability of task - parameterized movement models In Proc of Int Conf on Intelligent Robots and Systems pages","author":"Calinon","year":"2013","journal-title":"IEEE"},{"key":"ref181","first-page":"561","article-title":"Learning movement primitives In pages","author":"Schaal","year":"2005","journal-title":"Robotics Research"},{"key":"ref201","first-page":"828","article-title":"Segmentation and coupling in complex movements Humam Perception and Performence","volume":"11","author":"Viviani","year":"1985","journal-title":"Journal Experimental Psychology"},{"key":"ref331","first-page":"3843","article-title":"Motor learning by field approximation National Academy of","volume":"93","author":"Gandolfo","year":"1996","journal-title":"Sciences"},{"key":"ref381","doi-asserted-by":"crossref","first-page":"1000426","DOI":"10.1371\/journal.pcbi.1000426","article-title":"Movement timing and invariance arise from several geometries","volume":"5","author":"Bennequin","year":"2009","journal-title":"PLoS computational biology"},{"key":"ref451","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1038\/35039000","article-title":"d Avella New perspectives on spinal motor systems","volume":"1","author":"Bizzi","year":"2000","journal-title":"Nature Reviews Neuroscience"},{"key":"ref361","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1007\/s002210050606","article-title":"Segmentation of endpoint trajectories does not imply segmented control","volume":"124","author":"Sternad","year":"1999","journal-title":"Experimental Brain Research"},{"key":"ref341","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1152\/jn.1997.78.1.554","article-title":"The motor system does not learn the dynamics of the arm by rote memorization of past experience","volume":"78","author":"Conditt","year":"1997","journal-title":"Neurophysiology"},{"key":"ref241","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1016\/j.robot.2012.09.020","article-title":"Models of human movement : trajectory planning and inverse kinematics studies Robotics and","volume":"61","author":"Flash","year":"2013","journal-title":"Autonomous Systems"}],"container-title":["Paladyn, Journal of Behavioral Robotics"],"original-title":[],"link":[{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/pjbr-2015-0002\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T04:00:14Z","timestamp":1619064014000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyter.com\/document\/doi\/10.1515\/pjbr-2015-0002\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,10]]},"references-count":36,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1515\/pjbr-2015-0002","relation":{},"ISSN":["2081-4836"],"issn-type":[{"value":"2081-4836","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1,10]]}}}