{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T14:51:58Z","timestamp":1776783118020,"version":"3.51.2"},"reference-count":63,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2021,10,8]],"date-time":"2021-10-08T00:00:00Z","timestamp":1633651200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2021R1G1A1009792"],"award-info":[{"award-number":["2021R1G1A1009792"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Human-robot interaction has received a lot of attention as collaborative robots became widely utilized in many industrial fields. Among techniques for human-robot interaction, collision identification is an indispensable element in collaborative robots to prevent fatal accidents. This paper proposes a deep learning method for identifying external collisions in 6-DoF articulated robots. The proposed method expands the idea of CollisionNet, which was previously proposed for collision detection, to identify the locations of external forces. The key contribution of this paper is uncertainty-aware knowledge distillation for improving the accuracy of a deep neural network. Sample-level uncertainties are estimated from a teacher network, and larger penalties are imposed for uncertain samples during the training of a student network. Experiments demonstrate that the proposed method is effective for improving the performance of collision identification.<\/jats:p>","DOI":"10.3390\/s21196674","type":"journal-article","created":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T21:37:49Z","timestamp":1633901869000},"page":"6674","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Uncertainty-Aware Knowledge Distillation for Collision Identification of Collaborative Robots"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3656-2043","authenticated-orcid":false,"given":"Wookyong","family":"Kwon","sequence":"first","affiliation":[{"name":"Daegu-Gyeongbuk Research Center, Electronics and Telecommunications Research Institute (ETRI), Daegu 42994, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0487-0241","authenticated-orcid":false,"given":"Yongsik","family":"Jin","sequence":"additional","affiliation":[{"name":"Daegu-Gyeongbuk Research Center, Electronics and Telecommunications Research Institute (ETRI), Daegu 42994, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9312-6299","authenticated-orcid":false,"given":"Sang Jun","family":"Lee","sequence":"additional","affiliation":[{"name":"Division of Electronic Engineering, Jeonbuk National University, 567 Baekje-daero, Deokjin-gu, Jeonju 54896, Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,10,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Goodrich, M.A., and Schultz, A.C. (2008). Human-Robot Interaction: A Survey, Now Publishers Inc.","DOI":"10.1561\/9781601980939"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1007\/s10514-017-9677-2","article-title":"Progress and prospects of the human\u2013robot collaboration","volume":"42","author":"Ajoudani","year":"2018","journal-title":"Auton. Rob."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/TMRB.2019.2913282","article-title":"Autonomy for surgical robots: Concepts and paradigms","volume":"1","author":"Haidegger","year":"2019","journal-title":"IEEE Trans. Med. Rob. Bionics"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Berezina, K., Ciftci, O., and Cobanoglu, C. (2020). Robots, Artificial Intelligence, and Service Automation in Restaurants, Emerald Group Publishing.","DOI":"10.1108\/978-1-78756-687-320191010"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1016\/j.cogsys.2018.10.032","article-title":"Robot-enabled support of daily activities in smart home environments","volume":"54","author":"Wilson","year":"2019","journal-title":"Cognitive Syst. Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1590\/1678-457x.14616","article-title":"Prospects of robotics in food industry","volume":"37","author":"Iqbal","year":"2017","journal-title":"Food Sci. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.rcim.2018.11.004","article-title":"Human intention estimation based on hidden Markov model motion validation for safe flexible robotized warehouses","volume":"57","author":"Puljiz","year":"2019","journal-title":"Rob. Comput. Integr. Manuf."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Oudah, M., Al-Naji, A., and Chahl, J. (2020). Hand gesture recognition based on computer vision: A review of techniques. J. Imaging, 6.","DOI":"10.3390\/jimaging6080073"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"040802","DOI":"10.1115\/1.4046238","article-title":"Collaborative robotics: A survey","volume":"143","author":"Vicentini","year":"2021","journal-title":"J. Mech. Des."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5204","DOI":"10.1109\/TII.2019.2900119","article-title":"A sensorless hand guiding scheme based on model identification and control for industrial robot","volume":"15","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Ind. Inf."},{"key":"ref_11","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. Rob."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Morikawa, S., Senoo, T., Namiki, A., and Ishikawa, M. (2007, January 10\u201314). Realtime collision avoidance using a robot manipulator with light-weight small high-speed vision systems. Proceedings of the 2007 IEEE International Conference on Robotics and Automation (ICRA), Roma, Italy.","DOI":"10.1109\/ROBOT.2007.363083"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Mohammadi Amin, F., Rezayati, M., van de Venn, H.W., and Karimpour, H. (2020). A mixed-perception approach for safe human\u2013robot collaboration in industrial automation. Sensors, 20.","DOI":"10.20944\/preprints202009.0119.v1"},{"key":"ref_14","unstructured":"Lu, S., Chung, J.H., and Velinsky, S.A. (2005, January 18\u201322). Human-robot collision detection and identification based on wrist and base force\/torque sensors. Proceedings of the 2005 IEEE international Conference on Robotics and Automation (ICRA), Barcelona, Spain."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Lee, S.D., Kim, M.C., and Song, J.B. (October, January 28). Sensorless collision detection for safe human-robot collaboration. Proceedings of the 2015 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany.","DOI":"10.1109\/IROS.2015.7353701"},{"key":"ref_16","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_17","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 (IROS), Beijing, China.","DOI":"10.1109\/IROS.2006.282053"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Briquet-Kerestedjian, N., Makarov, M., Grossard, M., and Rodriguez-Ayerbe, P. (2017, January 27\u201330). Generalized momentum based-observer for robot impact detection\u2014Insights and guidelines under characterized uncertainties. Proceedings of the 2017 IEEE Conference on Control Technology and Applications (CCTA), Maui, HI, USA.","DOI":"10.1109\/CCTA.2017.8062635"},{"key":"ref_19","first-page":"162","article-title":"Practical aspects of model-based collision detection","volume":"7","author":"Mamedov","year":"2020","journal-title":"Front. Rob. AI"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Geravand, M., Flacco, F., and De Luca, A. (2013, January 6\u201310). Human-robot physical interaction and collaboration using an industrial robot with a closed control architecture. Proceedings of the 2013 IEEE International Conference on Robotics and Automation (ICRA), Karlsruhe, Germany.","DOI":"10.1109\/ICRA.2013.6631141"},{"key":"ref_21","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_22","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 Rob. Autom. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"3365","DOI":"10.1109\/TIE.2017.2748056","article-title":"Contact force estimation for robot manipulator using semiparametric model and disturbance Kalman filter","volume":"65","author":"Hu","year":"2017","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1016\/j.conengprac.2018.07.004","article-title":"Collision detection and identification for robot manipulators based on extended state observer","volume":"79","author":"Ren","year":"2018","journal-title":"Control Eng. Pract."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"720","DOI":"10.1109\/LRA.2017.2789249","article-title":"A frequency domain approach for contact type distinction in human\u2013robot collaboration","volume":"3","author":"Kouris","year":"2018","journal-title":"IEEE Rob. Autom. Lett."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"169","DOI":"10.7746\/jkros.2020.15.2.169","article-title":"A Comparative Study on Collision Detection Algorithms based on Joint Torque Sensor using Machine Learning","volume":"15","author":"Jo","year":"2020","journal-title":"J. Korea Robot. Soc."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"46","DOI":"10.15302\/J-ENG-2015009","article-title":"Efficient configuration space construction and optimization for motion planning","volume":"1","author":"Pan","year":"2015","journal-title":"Engineering"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1144","DOI":"10.1109\/TASE.2020.2997094","article-title":"An online robot collision detection and identification scheme by supervised learning and bayesian decision theory","volume":"18","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_29","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 Rob. Autom. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Caldas, A., Makarov, M., Grossard, M., Rodriguez-Ayerbe, P., and Dumur, D. (2013, January 9\u201312). Adaptive residual filtering for safe human-robot collision detection under modeling uncertainties. Proceedings of the 2013 IEEE\/ASME International Conference on Advanced Intelligent Mechatronics, Wollongong, Australia.","DOI":"10.1109\/AIM.2013.6584178"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1109\/TMECH.2014.2315440","article-title":"Adaptive filtering for robust proprioceptive robot impact detection under model uncertainties","volume":"19","author":"Makarov","year":"2014","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"6544","DOI":"10.1109\/LRA.2020.3015187","article-title":"Model-Adaptive High-Speed Collision Detection for Serial-Chain Robot Manipulators","volume":"5","author":"Birjandi","year":"2020","journal-title":"IEEE Rob. Autom. Lett."},{"key":"ref_33","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_34","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_35","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1109\/LRA.2020.3033269","article-title":"Learning-based real-time detection of robot collisions without joint torque sensors","volume":"6","author":"Park","year":"2020","journal-title":"IEEE Rob. Autom. Lett."},{"key":"ref_36","unstructured":"Oord, A.V.D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., and Kavukcuoglu, K. (2016). Wavenet: A generative model for raw audio. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Maceira, M., Olivares-Alarcos, A., and Alenya, G. (September, January 31). Recurrent neural networks for inferring intentions in shared tasks for industrial collaborative robots. Proceedings of the 2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Naples, Italy.","DOI":"10.1109\/RO-MAN47096.2020.9223587"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Czubenko, M., and Kowalczuk, Z. (2021). A Simple Neural Network for Collision Detection of Collaborative Robots. Sensors, 21.","DOI":"10.3390\/s21124235"},{"key":"ref_39","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the knowledge in a neural network. arXiv."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., and Cho, M. (2019, January 15\u201320). Relational knowledge distillation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Meng, Z., Li, J., Zhao, Y., and Gong, Y. (2019, January 12\u201317). Conditional teacher-student learning. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8683438"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Yim, J., Joo, D., Bae, J., and Kim, J. (2017, January 21\u201326). A gift from knowledge distillation: Fast optimization, network minimization and transfer learning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref_43","unstructured":"Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., and Bengio, Y. (2014). Fitnets: Hints for thin deep nets. arXiv."},{"key":"ref_44","unstructured":"Zagoruyko, S., and Komodakis, N. (2016). Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer. arXiv."},{"key":"ref_45","unstructured":"Yim, J., Joo, D., Bae, J., and Kim, J. (2017, January 4\u20137). Learning efficient object detection models with knowledge distillation. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Hou, Y., Ma, Z., Liu, C., Hui, T.W., and Loy, C.C. (2020, January 13\u201319). Inter-region affinity distillation for road marking segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01250"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Gupta, S., Hoffman, J., and Malik, J. (2016, January 27\u201330). Cross modal distillation for supervision transfer. Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Papernot, N., McDaniel, P., Wu, X., Jha, S., and Swami, A. (2016, January 22\u201326). Distillation as a defense to adversarial perturbations against deep neural networks. Proceedings of the 2016 IEEE symposium on security and privacy (SP), San Jose, CA, USA.","DOI":"10.1109\/SP.2016.41"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., and Wang, J. (2019, January 15\u201320). Structured knowledge distillation for semantic segmentation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00271"},{"key":"ref_50","unstructured":"Tarvainen, A., and Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1038\/nature14541","article-title":"Probabilistic machine learning and artificial intelligence","volume":"521","author":"Ghahramani","year":"2015","journal-title":"Nature"},{"key":"ref_52","unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 19\u201324). Dropout as a bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the 33rd international conference on machine learning, New York, NY, USA."},{"key":"ref_53","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_54","unstructured":"Lakshminarayanan, B., Pritzel, A., and Blundell, C. (2016). Simple and scalable predictive uncertainty estimation using deep ensembles. arXiv."},{"key":"ref_55","unstructured":"Van Amersfoort, J., Smith, L., Teh, Y.W., and Gal, Y. (2020, January 12\u201318). Uncertainty estimation using a single deep deterministic neural network. Proceedings of the 37rd International Conference on Machine Learning, Online."},{"key":"ref_56","unstructured":"Zhang, Z., Dalca, A.V., and Sabuncu, M.R. (2019). Confidence calibration for convolutional neural networks using structured dropout. arXiv."},{"key":"ref_57","unstructured":"Tagasovska, N., and Lopez-Paz, D. (2018). Single-model uncertainties for deep learning. arXiv."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Shen, Y., Zhang, Z., Sabuncu, M.R., and Sun, L. (2021, January 5\u20139). Real-time uncertainty estimation in computer vision via uncertainty-aware distribution distillation. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Online.","DOI":"10.1109\/WACV48630.2021.00075"},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Jin, X., Lan, C., Zeng, W., and Chen, Z. (2020, January 7\u201312). Uncertainty-aware multi-shot knowledge distillation for image-based object re-identification. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA.","DOI":"10.1609\/aaai.v34i07.6774"},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"3868","DOI":"10.1109\/TMI.2020.3006437","article-title":"Confidence calibration and predictive uncertainty estimation for deep medical image segmentation","volume":"39","author":"Mehrtash","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_61","doi-asserted-by":"crossref","unstructured":"Oh, D., Ji, D., Jang, C., Hyunv, Y., Bae, H.S., and Hwang, S. (August, January 31). Segmenting 2k-videos at 36.5 fps with 24.3 gflops: Accurate and lightweight realtime semantic segmentation network. Proceedings of the 2020 IEEE International Conference on Robotics and Automation (ICRA), Online.","DOI":"10.1109\/ICRA40945.2020.9196510"},{"key":"ref_62","first-page":"35","article-title":"Collision Identification of Collaborative Robots Using a Deep Neural Network","volume":"16","author":"Kwon","year":"2021","journal-title":"IEMEK J. Embed. Syst. Appl."},{"key":"ref_63","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/19\/6674\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:10:29Z","timestamp":1760166629000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/19\/6674"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,8]]},"references-count":63,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2021,10]]}},"alternative-id":["s21196674"],"URL":"https:\/\/doi.org\/10.3390\/s21196674","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,8]]}}}