{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:57:55Z","timestamp":1778083075357,"version":"3.51.4"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T00:00:00Z","timestamp":1673481600000},"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:p>Most motion planners generate trajectories as low-level control inputs, such as joint torque or interpolation of joint angles, which cannot be deployed directly in most industrial robot control systems. Some industrial robot systems provide interfaces to execute planned trajectories by an additional control loop with low-level control inputs. However, there is a geometric and temporal deviation between the executed and the planned motions due to the inaccurate estimation of the inaccessible robot dynamic behavior and controller parameters in the planning phase. This deviation can lead to collisions or dangerous situations, especially in heavy-duty industrial robot applications where high-speed and long-distance motions are widely used. When deploying the planned robot motion, the actual robot motion needs to be iteratively checked and adjusted to avoid collisions caused by the deviation between the planned and the executed motions. This process takes a lot of time and engineering effort. Therefore, the state-of-the-art methods no longer meet the needs of today\u2019s agile manufacturing for robotic systems that should rapidly plan and deploy new robot motions for different tasks. We present a data-driven motion planning approach using a neural network structure to simultaneously learn high-level motion commands and robot dynamics from acquired realistic collision-free trajectories. The trained neural network can generate trajectory in the form of high-level commands, such as Point-to-Point and Linear motion commands, which can be executed directly by the robot control system. The result carried out in various experimental scenarios has shown that the geometric and temporal deviation between the executed and the planned motions by the proposed approach has been significantly reduced, even if without access to the \u201cblack box\u201d parameters of the robot. Furthermore, the proposed approach can generate new collision-free trajectories up to 10 times faster than benchmark motion planners.<\/jats:p>","DOI":"10.3389\/frobt.2022.1030668","type":"journal-article","created":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T04:27:39Z","timestamp":1673497659000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["A data-driven approach for motion planning of industrial robots controlled by high-level motion commands"],"prefix":"10.3389","volume":"9","author":[{"given":"Shuxiao","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamad","family":"Bdiwi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aquib","family":"Rashid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Krusche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steffen","family":"Ihlenfeldt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,1,12]]},"reference":[{"key":"B1","first-page":"5542","article-title":"Human-robot-cooperation real time robot path planning for dynamic HRC-applications","author":"Bdiwi","year":"2018"},{"key":"B2","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/s1474-6670(17)46044-7","article-title":"The realistic robot simulation (rrs) interface","volume":"27","author":"Bernhardt","year":"1994","journal-title":"IFAC Proc. Volumes IFAC Workshop Intelligent Manuf. Syst."},{"key":"B3","first-page":"271","article-title":"Learning heuristic search via imitation","author":"Bhardwaj","year":"2017"},{"key":"B4","unstructured":"Learning an optimal sampling distribution for efficient motion planning74857492\n            ChengR.\n            ShankarK.\n            BurdickJ. W.\n          IEEE2020"},{"key":"B5","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/mra.2011.2181749","article-title":"Moveit![ros topics]","volume":"19","author":"Chitta","year":"2012","journal-title":"IEEE Robotics Automation Mag."},{"key":"B6","doi-asserted-by":"publisher","first-page":"116714","DOI":"10.1016\/j.eswa.2022.116714","article-title":"Reinforcement learning-based saturated adaptive robust neural-network control of underactuated autonomous underwater vehicles","volume":"197","author":"Elhaki","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"B7","doi-asserted-by":"publisher","first-page":"104106","DOI":"10.1016\/j.robot.2022.104106","article-title":"Output-feedback robust saturated actor\u2013critic multi-layer neural network controller for multi-body electrically driven tractors with n-trailer guaranteeing prescribed output constraints","volume":"154","author":"Elhaki","year":"2022","journal-title":"Robot. Aut. Syst."},{"key":"B8","first-page":"715","article-title":"Learning-based adaptive sampling for manipulator motion planning","author":"Gaebert","year":"2022"},{"key":"B9","first-page":"2493","article-title":"Fast smoothing of manipulator trajectories using optimal bounded-acceleration shortcuts","author":"Hauser","year":"2010"},{"key":"B10","doi-asserted-by":"publisher","first-page":"3868","DOI":"10.1109\/lra.2018.2856927","article-title":"Efficient sampling with q-learning to guide rapidly exploring random trees","volume":"3","author":"Huh","year":"2018","journal-title":"IEEE Robotics Automation Lett."},{"key":"B11","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1177\/0278364915577958","article-title":"Fast marching tree: A fast marching sampling-based method for optimal motion planning in many dimensions","volume":"34","author":"Janson","year":"2015","journal-title":"Int. J. Robotics Res."},{"key":"B12","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/tpami.2012.59","article-title":"3D convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2013","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B13","volume-title":"Neural cost-to-go function representation for high dimensional motion planning. Workshop: Motion planning with implicit neural representations of geometry","author":"Jinwook","year":"2022"},{"key":"B14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.15607\/RSS.2019.XV.026","article-title":"Harnessing reinforcement learning for neural motion planning","volume-title":"Robotics: Science and systems","author":"Jurgenson","year":"2019"},{"key":"B15","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1177\/0278364911406761","article-title":"Sampling-based algorithms for optimal motion planning","volume":"30","author":"Karaman","year":"2011","journal-title":"Int. J. Robotics Res."},{"key":"B16","article-title":"A method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"B17","first-page":"1","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014"},{"key":"B18","first-page":"995","article-title":"RRT-connect: An efficient approach to single-query path planning","author":"Kuffner","year":"2000"},{"key":"B19","volume-title":"Rapidly-exploring random trees: A new tool for path planning","author":"LaValle","year":"1998"},{"key":"B20","doi-asserted-by":"crossref","DOI":"10.1109\/ICRA40945.2020.9196833","article-title":"Learn and link: Learning critical regions for efficient planning","author":"Molina","year":"2020"},{"key":"B21","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1007\/978-3-662-62962-8_52","article-title":"Combining safe collaborative and high-accuracy operations in industrial robots","volume-title":"Advances in automotive production Technology \u2013 theory and application","author":"Otto","year":"2021"},{"key":"B22","first-page":"3859","article-title":"Fcl: A general purpose library for collision and proximity queries","author":"Pan","year":"2012"},{"key":"B23","article-title":"Ros: An open-source robot operating system","author":"Quigley","year":"2009"},{"key":"B24","first-page":"2118","article-title":"Motion planning networks","author":"Qureshi","year":"2019"},{"key":"B25","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/tro.2020.3006716","article-title":"Motion planning networks: Bridging the gap between learning-based and classical motion planners","volume":"37","author":"Qureshi","year":"2020","journal-title":"IEEE Trans. Robotics"},{"key":"B26","doi-asserted-by":"crossref","first-page":"312","DOI":"10.22266\/ijies2021.0831.28","article-title":"Fault tolerant control of robot manipulators based on adaptive fuzzy type-2 backstepping in attendance of payload variation","volume":"14","author":"Rahali","year":"2022","journal-title":"International Journal of Intelligent Engineering and Systems"},{"key":"B27","first-page":"489","article-title":"Chomp: Gradient optimization techniques for efficient motion planning","author":"Ratliff","year":"2009"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.1177\/0278364914528132","article-title":"Motion planning with sequential convex optimization and convex collision checking","volume":"33","author":"Schulman","year":"2014","journal-title":"Int. J. Robotics Res."},{"key":"B29","first-page":"1","article-title":"Finding locally optimal, collision-free trajectories with sequential convex optimization","volume":"9","author":"Schulman","year":"2013","journal-title":"Robot. Sci. Syst."},{"key":"B30","article-title":"Using deep learning to bootstrap abstractions for hierarchical robot planning","author":"Shah","year":"2022"},{"key":"B31","doi-asserted-by":"publisher","first-page":"102476","DOI":"10.1016\/j.rcim.2022.102476","article-title":"A prediction and compensation method of robot tracking error considering pose-dependent load decomposition","volume":"80","author":"Tan","year":"2023","journal-title":"Robotics Computer-Integrated Manuf."},{"key":"B32","volume-title":"Visual components","year":"2021"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1177\/0278364913488805","article-title":"Chomp: Covariant Hamiltonian optimization for motion planning","volume":"32","author":"Zucker","year":"2013","journal-title":"Int. J. Robotics Res."}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2022.1030668\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T04:27:49Z","timestamp":1673497669000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2022.1030668\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,12]]},"references-count":33,"alternative-id":["10.3389\/frobt.2022.1030668"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2022.1030668","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,12]]},"article-number":"1030668"}}