{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T18:48:23Z","timestamp":1769366903798,"version":"3.49.0"},"reference-count":48,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T00:00:00Z","timestamp":1624233600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005632","name":"Narodowe Centrum Bada\u0144 i Rozwoju","doi-asserted-by":"publisher","award":["POIR.01.01.01-00-0074\/17"],"award-info":[{"award-number":["POIR.01.01.01-00-0074\/17"]}],"id":[{"id":"10.13039\/501100005632","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Due to the epidemic threat, more and more companies decide to automate their production lines. Given the lack of adequate security or space, in most cases, such companies cannot use classic production robots. The solution to this problem is the use of collaborative robots (cobots). However, the required equipment (force sensors) or alternative methods of detecting a threat to humans are usually quite expensive. The article presents the practical aspect of collision detection with the use of a simple neural architecture. A virtual force and torque sensor, implemented as a neural network, may be useful in a team of collaborative robots. Four different approaches are compared in this article: auto-regressive (AR), recurrent neural network (RNN), convolutional long short-term memory (CNN-LSTM) and mixed convolutional LSTM network (MC-LSTM). These architectures are analyzed at different levels of input regression (motor current, position, speed, control velocity). This sensor was tested on the original CURA6 robot prototype (Cooperative Universal Robotic Assistant 6) by Intema. The test results indicate that the MC-LSTM architecture is the most effective with the regression level set at 12 samples (at 24 Hz). The mean absolute prediction error obtained by the MC-LSTM architecture was approximately 22 Nm. The conducted external test (72 different signals with collisions) shows that the presented architecture can be used as a collision detector. The MC-LSTM collision detection f1 score with the optimal threshold was 0.85. A well-developed virtual sensor based on such a network can be used to detect various types of collisions of cobot or other mobile or stationary systems operating on the basis of human-machine interaction.<\/jats:p>","DOI":"10.3390\/s21124235","type":"journal-article","created":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T13:29:58Z","timestamp":1624282198000},"page":"4235","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["A Simple Neural Network for Collision Detection of Collaborative Robots"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9483-4983","authenticated-orcid":false,"given":"Micha\u0142","family":"Czubenko","sequence":"first","affiliation":[{"name":"Department of Robotics and Decision Systems, Faculty of Electronics Telecommunications and Informatics, Gda\u0144sk University of Technology, Narutowicza 11\/12, 80-233 Gda\u0144sk, Poland"},{"name":"Intema Sp. z o. o., Siennicka 25a, 80-758 Gda\u0144sk, Poland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9174-546X","authenticated-orcid":false,"given":"Zdzis\u0142aw","family":"Kowalczuk","sequence":"additional","affiliation":[{"name":"Department of Robotics and Decision Systems, Faculty of Electronics Telecommunications and Informatics, Gda\u0144sk University of Technology, Narutowicza 11\/12, 80-233 Gda\u0144sk, Poland"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,21]]},"reference":[{"key":"ref_1","unstructured":"Eurostat (2019). Job Vacancies between 2017 and 2019, Eurostat. Available online: https:\/\/ec.europa.eu\/eurostat\/statistics-explained\/index.php\/Job_vacancy_statistics."},{"key":"ref_2","unstructured":"International Federation of Robotics (IFR) (2020). Industrial Robots: Robot Investment Reaches Record 16.5 Billion USD, IFR. Available online: https:\/\/ifr.org\/ifr-press-releases\/news\/robot-investment-reaches-record-16.5-billion-usd."},{"key":"ref_3","unstructured":"Colgate, J.E., and Peshkin, M.A. (1999). Cobots. (5,952,796), U.S. Patent."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"103562","DOI":"10.1016\/j.engappai.2020.103562","article-title":"Interpretation and modeling of emotions in the management of autonomous robots using a control paradigm based on a scheduling variable","volume":"91","author":"Kowalczuk","year":"2020","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.mechatronics.2018.02.009","article-title":"Survey on human\u2013robot collaboration in industrial settings: Safety, intuitive interfaces and applications","volume":"55","author":"Villani","year":"2018","journal-title":"Mechatronics"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"41","DOI":"10.14313\/PAR_234\/41","article-title":"Safety system for an industrial cooperating robot based on depth cameras","volume":"23","author":"Czubenko","year":"2019","journal-title":"Pomiary Autom. Robot."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"102399","DOI":"10.1016\/j.mechatronics.2020.102399","article-title":"Set-based collision avoidance applications to robotic systems","volume":"69","author":"Moe","year":"2020","journal-title":"Mechatronics"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1109\/TMECH.2015.2496553","article-title":"A limb compliant sensing strategy for robot collision reaction","volume":"21","author":"Miyata","year":"2015","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TMECH.2015.2415462","article-title":"Reactive task adaptation based on hierarchical constraints classification for safe industrial robots","volume":"20","author":"Ceriani","year":"2015","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.mechatronics.2018.01.016","article-title":"A virtual force sensor for interaction tasks with conventional industrial robots","volume":"50","author":"Villagrossi","year":"2018","journal-title":"Mechatronics"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"621","DOI":"10.2478\/v10006-011-0053-7","article-title":"Intelligent decision-making system for autonomous robots","volume":"21","author":"Kowalczuk","year":"2011","journal-title":"Int. J. Appl. Math. Comput. Sci."},{"key":"ref_12","unstructured":"Varhegyi, T., Melik-Merkumians, M., Steinegger, M., Halmetschlager-Funek, G., and Schitter, G. (2017). A Visual Servoing Approach for a Six Degrees-of-Freedom Industrial Robot by RGB-D Sensing. Autom. Robot."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., and Sheikh, Y. (2018). OpenPose: Realtime multi-person 2D pose estimation using Part Affinity Fields. arXiv.","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/s10846-018-0781-0","article-title":"Neural network based adaptive actuator fault detection algorithm for robot manipulators","volume":"95","author":"Cho","year":"2019","journal-title":"J. Intell. Robot. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1109\/LRA.2019.2893400","article-title":"Collision detection for industrial collaborative robots: A deep learning approach","volume":"4","author":"Heo","year":"2019","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"De Luca, A., Albu-Schaffer, A., Haddadin, S., and Hirzinger, G. (2006, January 9\u201315). Collision detection and safe reaction with the DLR-III lightweight manipulator arm. Proceedings of the 2006 IEEE\/RSJ International Conference on Intelligent Robots and Systems, Beijing, China.","DOI":"10.1109\/IROS.2006.282053"},{"key":"ref_17","first-page":"150","article-title":"Human-robot collision detection based on neural networks","volume":"7","author":"Sharkawy","year":"2018","journal-title":"Int. J. Mech. Eng. Robot. Res."},{"key":"ref_18","unstructured":"Shi, X., Zhourong, C., Hao, W., Dit-Yan, Y., Wai-Kin, W., and Wang-chun, W. (2015, January 11\u201312). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Proceedings of the 29th Annual Conference on Neural Information Processing Systems (NIPS 2015), Montreal, QC, Canada."},{"key":"ref_19","unstructured":"Koz\u0142owski, K. (1998). Modeling and Identification in Robotics, Springer."},{"key":"ref_20","first-page":"471478","article-title":"Dynamic model identification for 6-DOF industrial robots","volume":"2015","author":"Ding","year":"2015","journal-title":"J. Robot."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.rcim.2014.06.004","article-title":"Parameter identification for industrial robots with a fast and robust trajectory design approach","volume":"31","author":"Jin","year":"2015","journal-title":"Robot. Comput. Integr. Manuf."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kowalczuk, Z., and Merta, T. (2017, January 28\u201331). Estimation of DC motor parameters using a simple CMOS camera. Proceedings of the 22nd International Conference on Methods and Models in Automation and Robotics, Mi\u0119dzyzdroje, Poland.","DOI":"10.1109\/MMAR.2017.8046943"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1016\/j.rcim.2010.03.013","article-title":"An overview of dynamic parameter identification of robots","volume":"26","author":"Wu","year":"2010","journal-title":"Robot. Comput. Integr. Manuf."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"108795","DOI":"10.1109\/ACCESS.2019.2931515","article-title":"Force\/torque sensorless compliant control strategy for assembly tasks using a 6-DOF collaborative robot","volume":"7","author":"Zeng","year":"2019","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1017\/S0263574706002712","article-title":"Fourier-based optimal excitation trajectories for the dynamic identification of robots","volume":"24","author":"Park","year":"2006","journal-title":"Robotica"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1109\/TRO.2017.2723903","article-title":"Robot collisions: A survey on detection, isolation, and identification","volume":"33","author":"Haddadin","year":"2017","journal-title":"IEEE Trans. Robot."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Indri, M., Trapani, S., and Lazzero, I. (2017). Development of a virtual collision sensor for industrial robots. Sensors, 17.","DOI":"10.3390\/s17051148"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Mariotti, E., Magrini, E., and De Luca, A. (2019, January 20\u201324). Admittance Control for Human-Robot Interaction Using an Industrial Robot Equipped with a F\/T Sensor. Proceedings of the 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada.","DOI":"10.1109\/ICRA.2019.8793657"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Li, Z., Ye, J., and Wu, H. (2019). A virtual sensor for collision detection and distinction with conventional industrial robots. Sensors, 19.","DOI":"10.3390\/s19102368"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"175","DOI":"10.3233\/JIFS-179392","article-title":"A new robot collision detection method: A modified nonlinear disturbance observer based-on neural networks","volume":"38","author":"Xu","year":"2020","journal-title":"J. Intell. Fuzzy Syst."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, S., Ye, J., Li, Z., Li, S., Wu, G., and Wu, H. (2015, January 6\u20139). A momentum-based collision detection algorithm for industrial robots. Proceedings of the 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO), Zhuhai, China.","DOI":"10.1109\/ROBIO.2015.7418943"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2261","DOI":"10.1109\/TMECH.2019.2934141","article-title":"Collision Detection and Coordinated Compliance Control for a Dual-Arm Robot Without Force\/Torque Sensing Based on Momentum Observer","volume":"24","author":"Han","year":"2019","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1108\/IR-01-2018-0019","article-title":"Manipulator residual estimation and its application in collision detection","volume":"45","author":"Guo","year":"2018","journal-title":"Ind. Robot Int. J."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Popov, D., Klimchik, A., and Mavridis, N. (September, January 28). Collision detection, localization & classification for industrial robots with joint torque sensors. Proceedings of the 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), Lisbon, Portugal.","DOI":"10.1109\/ROMAN.2017.8172400"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Chen, S., Luo, M., and He, F. (2018). A universal algorithm for sensorless collision detection of robot actuator faults. Adv. Mech. Eng., 10.","DOI":"10.1177\/1687814017740710"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1737","DOI":"10.1017\/S0263574719000985","article-title":"Neural network design for manipulator collision detection based only on the joint position sensors","volume":"38","author":"Sharkawy","year":"2020","journal-title":"Robotica"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1109\/87.491201","article-title":"Observer-based supervision and fault detection in robots using nonlinear and fuzzy logic residual evaluation","volume":"4","author":"Sneider","year":"1996","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"041005","DOI":"10.1115\/1.4048782","article-title":"Robot Collision Detection Without External Sensors Based on Time-Series Analysis","volume":"143","author":"Zhang","year":"2021","journal-title":"J. Dyn. Syst. Meas. Control"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"954","DOI":"10.1109\/LRA.2020.2967287","article-title":"Observer-extended direct method for collision monitoring in robot manipulators using proprioception and imu sensing","volume":"5","author":"Birjandi","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Min, F., Wang, G., and Liu, N. (2019). Collision detection and identification on robot manipulators based on vibration analysis. Sensors, 19.","DOI":"10.3390\/s19051080"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"204","DOI":"10.3390\/electronics4010204","article-title":"Piezoelectric Polymer-Based Collision Detection Sensor for Robotic Applications","volume":"4","author":"Wooten","year":"2015","journal-title":"Electronics"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Pang, G., Deng, J., Wang, F., Zhang, J., Pang, Z., and Yang, G. (2018). Development of flexible robot skin for safe and natural human\u2013robot collaboration. Micromachines, 9.","DOI":"10.3390\/mi9110576"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1902","DOI":"10.1109\/TCST.2020.2998798","article-title":"Modified Line-of-Sight Guidance Law With Adaptive Neural Network Control of Underactuated Marine Vehicles With State and Input Constraints","volume":"28","author":"Rout","year":"2020","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Jiang, X. (1999). Time varying coefficient AR and VAR models. The Practice of Time Series Analysis, Springer.","DOI":"10.1007\/978-1-4612-2162-3_11"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Selvin, S., Vinayakumar, R., Gopalakrishnan, E., Menon, V.K., and Soman, K. (2017, January 13\u201316). Stock price prediction using LSTM, RNN and CNN-sliding window model. Proceedings of the 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Udupi, India.","DOI":"10.1109\/ICACCI.2017.8126078"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1016\/j.energy.2019.05.230","article-title":"Predicting residential energy consumption using CNN-LSTM neural networks","volume":"182","author":"Kim","year":"2019","journal-title":"Energy"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Grafarend, E., and Awange, J. (2012). Linear and Nonlinear Models: Fixed Effects, Random Effects, and Total Least Squares, Springer.","DOI":"10.1007\/978-3-642-22241-2"},{"key":"ref_48","unstructured":"Korbicz, J., Ko\u015bcielny, J.M., Kowalczuk, Z., and Cholewa, W. (2012). Fault Diagnosis: Models, Artificial Intelligence, Applications, Springer Science & Business Media."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4235\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:19:58Z","timestamp":1760163598000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,21]]},"references-count":48,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["s21124235"],"URL":"https:\/\/doi.org\/10.3390\/s21124235","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,21]]}}}