{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T15:03:11Z","timestamp":1774969391038,"version":"3.50.1"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030918842","type":"print"},{"value":"9783030918859","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-91885-9_18","type":"book-chapter","created":{"date-parts":[[2021,12,2]],"date-time":"2021-12-02T13:03:12Z","timestamp":1638450192000},"page":"251-265","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep Reinforcement Learning Applied to\u00a0a\u00a0Robotic Pick-and-Place Application"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2444-375X","authenticated-orcid":false,"given":"Natanael Magno","family":"Gomes","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1032-6162","authenticated-orcid":false,"given":"Felipe N.","family":"Martins","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7902-1207","authenticated-orcid":false,"given":"Jos\u00e9","family":"Lima","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2263-0495","authenticated-orcid":false,"given":"Heinrich","family":"W\u00f6rtche","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,1]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Siciliano, B., Khatib, O. (eds.): Springer Handbook of Robotics, pp. 1\u20132227. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-32552-1","DOI":"10.1007\/978-3-319-32552-1"},{"key":"18_CR2","unstructured":"ISO\/TS 15066 Robots and robotic devices - Collaborative robots. International Organization for Standardization, Geneva, CH, Standard, February 2016"},{"key":"18_CR3","doi-asserted-by":"publisher","unstructured":"Saxena, A., Driemeyer, J., Kearns, J., Ng, A.Y.: Robotic grasping of novel objects. In: Advances in Neural Information Processing Systems, pp. 1209\u20131216 (2007). https:\/\/doi.org\/10.7551\/mitpress\/7503.003.0156. ISBN: 9780262195683","DOI":"10.7551\/mitpress\/7503.003.0156"},{"key":"18_CR4","doi-asserted-by":"publisher","unstructured":"Torras, C.: Computer Vision: Theory and Industrial Applications, p. 455. Springer, Heidelberg (1992). https:\/\/doi.org\/10.1007\/978-3-642-48675-3. ISBN: 3642486754","DOI":"10.1007\/978-3-642-48675-3"},{"key":"18_CR5","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1007\/s00217-012-1844-2","volume":"235","author":"JFS Gomes","year":"2012","unstructured":"Gomes, J.F.S., Leta, F.R.: Applications of computer vision techniques in the agriculture and food industry: a review. Eur. Food Res. Technol. 235, 989\u20131000 (2012). https:\/\/doi.org\/10.1007\/s00217-012-1844-2","journal-title":"Eur. Food Res. Technol."},{"key":"18_CR6","doi-asserted-by":"publisher","unstructured":"Arakeri, M.P., Lakshmana: Computer vision based fruit grading system for quality evaluation of tomato in agriculture industry. Procedia Comput. Sci. 79, 426\u2013433 (2016). https:\/\/doi.org\/10.1016\/j.procs.2016.03.055","DOI":"10.1016\/j.procs.2016.03.055"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Bhutta, M.U.M., Aslam, S., Yun, P., Jiao, J., Liu, M.: Smart-inspect: micro scale localization and classification of smartphone glass defects for industrial automation. arXiv: 2010.00741, October 2020","DOI":"10.1109\/IROS45743.2020.9341509"},{"key":"18_CR8","doi-asserted-by":"publisher","unstructured":"Shafii, N., Kasaei, S.H., Lopes, L.S.: Learning to grasp familiar objects using object view recognition and template matching. In: IEEE International Conference on Intelligent Robots and Systems, vol. 2016-November, pp. 2895\u20132900. Institute of Electrical and Electronics Engineers Inc., November 2016. https:\/\/doi.org\/10.1109\/IROS.2016.7759448. ISBN: 9781509037629","DOI":"10.1109\/IROS.2016.7759448"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"Kumra, S., Kanan, C.: Robotic grasp detection using deep convolutional neural networks. In: IEEE International Conference on Intelligent Robots and Systems, vol. 2017-September, pp. 769\u2013776. Institute of Electrical and Electronics Engineers Inc., November 2017. https:\/\/doi.org\/10.1109\/IROS.2017.8202237. arXiv: 1611.08036. ISBN: 9781538626825","DOI":"10.1109\/IROS.2017.8202237"},{"key":"18_CR10","doi-asserted-by":"publisher","unstructured":"Morrison, D., Corke, P., Leitner, J.: Learning robust, real-time, reactive robotic grasping. Int. J. Robot. Res. 39(2\u20133), 183\u2013201 (2020). https:\/\/doi.org\/10.1177\/0278364919859066. ISSN: 0278-3649","DOI":"10.1177\/0278364919859066"},{"key":"18_CR11","doi-asserted-by":"publisher","unstructured":"Mittal, S., Vaishay, S.: A survey of techniques for optimizing deep learning on GPUs. J. Syst. Archit. 99, 101635 (2019). https:\/\/doi.org\/10.1016\/j.sysarc.2019.101635. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1383762119302656. ISSN: 1383-7621","DOI":"10.1016\/j.sysarc.2019.101635"},{"key":"18_CR12","unstructured":"Saha, S.: A comprehensive guide to convolutional neural networks - the ELI5 way - by Sumit Saha - towards data science (2018). https:\/\/towardsdatascience.com\/a-comprehensiveguide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53. Accessed 20 June 2020"},{"key":"18_CR13","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.81. arXiv: 1311.2524. ISBN: 9781479951178","DOI":"10.1109\/CVPR.2014.81"},{"key":"18_CR14","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, vol. 2015 Inter, pp. 1440\u20131448 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.169. arXiv: 1504.08083. ISSN: 15505499","DOI":"10.1109\/ICCV.2015.169"},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017). https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031. arXiv: 1506.01497. ISSN: 01628828","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"18_CR16","doi-asserted-by":"publisher","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. IEEE Trans. Pattern Anal. Mach. Intell. 42(2), 386\u2013397 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2018.2844175. arXiv: 1703.06870. ISSN: 19393539","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"18_CR17","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., He, K.: Detectron (2018). https:\/\/github.com\/facebookresearch\/detectron"},{"key":"18_CR18","unstructured":"Debkowski, D.: SuperBadCode\/Depth-Mask-RCNN: using Kinect2 depth sensors to train neural network for object detection & interaction. https:\/\/github.com\/SuperBadCode\/Depth-Mask-RCNN. Accessed 20 June 2020"},{"key":"18_CR19","unstructured":"Sutton, R.S. Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn, p. 552. The MIT Press, Cambridge (2018). ISBN: 978-0-262-03924-6"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Zanuttigh, P., Marin, G., Dal Mutto, C., Dominio, F., Minto, L., Cortelazzo, G.M.: Time-of-Flight and Structured Light Depth Cameras, pp. 1\u2013355. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-30973-6. ISBN: 9783319309736","DOI":"10.1007\/978-3-319-30973-6"},{"key":"18_CR21","unstructured":"Zhang, F., Leitner, J., Milford, M., Upcroft, B., Corke, P.: Towards vision-based deep reinforcement learning for robotic motion control. arXiv: 1511.03791, November 2015"},{"key":"18_CR22","doi-asserted-by":"publisher","unstructured":"Joshi, S., Kumra, S., Sahin, F.: Robotic grasping using deep reinforcement learning. In: 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE), pp. 1461\u20131466. IEEE, August 2020. https:\/\/doi.org\/10.1109\/CASE48305.2020.9216986. ISBN: 978-1-7281-6904-0","DOI":"10.1109\/CASE48305.2020.9216986"},{"key":"18_CR23","doi-asserted-by":"publisher","unstructured":"Rahman, M.D.M., Rashid, S.M.H., Hossain, M.M.: Implementation of Q learning and deep Q network for controlling a self balancing robot model. Robot. Biomim. 5(1), 1\u20136 (2018). https:\/\/doi.org\/10.1186\/s40638-018-0091-9. arXiv: 1807.08272. ISSN: 2197-3768","DOI":"10.1186\/s40638-018-0091-9"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Hase, H., Azampour, M.F., Tirindelli, M., et al.: Ultrasound-guided robotic navigation with deep reinforcement learning. arXiv: 2003.13321, March 2020","DOI":"10.1109\/IROS45743.2020.9340913"},{"key":"18_CR25","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. Technical Report. arXiv: 1608.06993v5. https:\/\/github.com\/liuzhuang13\/DenseNet"},{"key":"18_CR26","unstructured":"Torchvision.models (2019). https:\/\/pytorch.org\/docs\/stable\/torchvision\/models.html. Accessed 17 Jan 2021"},{"key":"18_CR27","unstructured":"Webots. Commercial Mobile Robot Simulation Software. Cyberbotics Ltd., Ed. https:\/\/www.cyberbotics.com"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Ayala, A., Cruz, F., Campos, D., Rubio, R., Fernandes, B., Dazeley, R.: A comparison of humanoid robot simulators: a quantitative approach, pp. 1\u201310. arXiv: 2008.04627 (2020)","DOI":"10.1109\/ICDL-EpiRob48136.2020.9278116"},{"key":"18_CR29","unstructured":"Rajeswaran, A., Kumar, V., Gupta, A., et al.: Learning complex dexterous manipulation with deep reinforcement learning and demonstrations. Technical Report. arXiv: 1709.10087v2. http:\/\/sites.google.com\/view\/deeprl-dexterous-manipulation"},{"key":"18_CR30","unstructured":"Hawkins, K.P.: Analytic inverse kinematics for the universal robots UR-5\/UR-10 arms. Technical Report, December 2013. https:\/\/smartech.gatech.edu\/handle\/1853\/50782"},{"key":"18_CR31","unstructured":"Universal Robots - Parameters for calculations of kinematics and dynamics. https:\/\/www.universal-robots.com\/articles\/ur\/parameters-for-calculations-of-kinematics-anddynamics\/. Accessed 31 Dec 2020"},{"key":"18_CR32","unstructured":"Manual Robotiq 2F-85 & 2F-140 for e-series universal robots, Robotic, 145 pp., November 2018"},{"key":"18_CR33","unstructured":"SmoothL1Loss \u2013 PyTorch 1.7.0 documentation. https:\/\/pytorch.org\/docs\/stable\/generated\/torch.nn.SmoothL1Loss.html. Accessed 15 Jan 2021"},{"key":"18_CR34","unstructured":"Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, December 2015. arXiv: 1412.6980"},{"key":"18_CR35","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization, November 2017. arXiv: 1711.05101. http:\/\/arxiv.org\/abs\/1711.05101"},{"key":"18_CR36","doi-asserted-by":"publisher","unstructured":"De Bruin, T., Kober, J., Tuyls, K., Babu\u0161ka, R.: Experience selection in deep reinforcement learning for control. J. Mach. Learn. Res. 19, 1\u201356 (2018). https:\/\/doi.org\/10.5555\/3291125.3291134. http:\/\/jmlr.org\/papers\/v19\/17-131.html. ISSN: 15337928","DOI":"10.5555\/3291125.3291134"},{"key":"18_CR37","unstructured":"Brys, T., Harutyunyan, A., Suay, H.B., Chernova, S., Taylor, M.E., Now\u00e9, A.: Reinforcement learning from demonstration through shaping. In: IJCAI International Joint Conference on Artificial Intelligence, vol. 2015-January, pp. 3352\u20133358 (2015). ISBN: 9781577357384"}],"container-title":["Communications in Computer and Information Science","Optimization, Learning Algorithms and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-91885-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,2]],"date-time":"2021-12-02T13:24:26Z","timestamp":1638451466000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-91885-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030918842","9783030918859"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-91885-9_18","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"1 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"OL2A","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Optimization, Learning Algorithms and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bragan\u00e7a","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ol2a2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ol2a.ipb.pt\/EN_index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"134","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"13","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"29% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to the COVID-19 pandemic the conference was held online.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}