{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:11:17Z","timestamp":1743009077263,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030890971"},{"type":"electronic","value":"9783030890988"}],"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\/978-3-030-89098-8_14","type":"book-chapter","created":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T10:32:10Z","timestamp":1634466730000},"page":"142-152","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Learning Robot Grasping from a Random Pile with Deep Q-Learning"],"prefix":"10.1007","author":[{"given":"Bin","family":"Chen","sequence":"first","affiliation":[]},{"given":"Jianhua","family":"Su","sequence":"additional","affiliation":[]},{"given":"Lili","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Qipeng","family":"Gu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,18]]},"reference":[{"key":"14_CR1","doi-asserted-by":"publisher","unstructured":"Goins, A.K., Carpenter, R., Wong, W.K., Balasubramanian, R.: Evaluating the efficacy of grasp metrics for utilization in a gaussian process-based grasp predictor. In: 2014 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 3353\u20133360 (2014). https:\/\/doi.org\/10.1109\/IROS.2014.6943029","DOI":"10.1109\/IROS.2014.6943029"},{"key":"14_CR2","doi-asserted-by":"publisher","unstructured":"Boularias, A., Kroemer, O., Peters, J.: Learning robot grasping from 3-d images with markov random fields. In: 2011 IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1548\u20131553 (2011). https:\/\/doi.org\/10.1109\/IROS.2011.6094888","DOI":"10.1109\/IROS.2011.6094888"},{"key":"14_CR3","doi-asserted-by":"publisher","unstructured":"Balaguer, B., Carpin, S.: Learning end-effector orientations for novel object grasping tasks. In: 2010 10th IEEE-RAS International Conference on Humanoid Robots, pp. 302\u2013307 (2010). https:\/\/doi.org\/10.1109\/ICHR.2010.5686826","DOI":"10.1109\/ICHR.2010.5686826"},{"issue":"2","key":"14_CR4","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1177\/0278364907087172","volume":"27","author":"A Saxena","year":"2008","unstructured":"Saxena, A., Driemeyer, J., Ng, A.Y.: Robotic grasping of novel objects using vision. Int. J. Rob. Res. 27(2), 157\u2013173 (2008)","journal-title":"Int. J. Rob. Res."},{"issue":"2","key":"14_CR5","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1109\/TRO.2013.2289018","volume":"30","author":"J Bohg","year":"2013","unstructured":"Bohg, J., Morales, A., Asfour, T., Kragic, D.: Data-driven grasp synthesis-a survey. IEEE Trans. Rob. 30(2), 289\u2013309 (2013)","journal-title":"IEEE Trans. Rob."},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Pinto, L., Gupta, A.: Supersizing self-supervision: Learning to grasp from 50k tries and 700 robot hours. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 3406\u20133413. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Mahler, J., et al.: Learning ambidextrous robot grasping policies. Sci. Rob. 4(26) (2019)","DOI":"10.1126\/scirobotics.aau4984"},{"issue":"7540","key":"14_CR8","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"7587","key":"14_CR9","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 3389\u20133396. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"14_CR11","unstructured":"Nair, A., Pong, V., Dalal, M., Bahl, S., Lin, S., Levine, S.: Visual reinforcement learning with imagined goals. arXiv preprint arXiv:1807.04742 (2018)"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Pinto, L., Andrychowicz, M., Welinder, P., Zaremba, W., Abbeel, P.: Asymmetric actor critic for image-based robot learning. arXiv preprint arXiv:1710.06542 (2017)","DOI":"10.15607\/RSS.2018.XIV.008"},{"key":"14_CR13","unstructured":"Popov, I., Heess, N., Lillicrap, T., Hafner, R., Barth-Maron, G., Vecerik, M., Lampe, T., Tassa, Y., Erez, T., Riedmiller, M.: Data-efficient deep reinforcement learning for dexterous manipulation. arXiv preprint arXiv:1704.03073 (2017)"},{"issue":"4\u20135","key":"14_CR14","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1177\/0278364917710318","volume":"37","author":"S Levine","year":"2018","unstructured":"Levine, S., Pastor, P., Krizhevsky, A., Ibarz, J., Quillen, D.: Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection. The International Journal of Robotics Research 37(4\u20135), 421\u2013436 (2018)","journal-title":"The International Journal of Robotics Research"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Sadeghi, F., Toshev, A., Jang, E., Levine, S.: Sim2real view invariant visual servoing by recurrent control. arXiv preprint arXiv:1712.07642 (2017)","DOI":"10.1109\/CVPR.2018.00493"},{"key":"14_CR16","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-030-36802-9_33","volume-title":"Neural Information Processing","author":"B Chen","year":"2019","unstructured":"Chen, B., Su, J.: Addressing reward engineering for deep reinforcement learning on multi-stage task. In: Gedeon, T., Wong, K.W., Lee, M. (eds.) ICONIP 2019. CCIS, vol. 1143, pp. 309\u2013317. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-36802-9_33"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Zeng, A., Song, S., Welker, S., Lee, J., Rodriguez, A., Funkhouser, T.: Learning synergies between pushing and grasping with self-supervised deep reinforcement learning. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4238\u20134245. IEEE (2018)","DOI":"10.1109\/IROS.2018.8593986"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Wiering, M., Van Otterlo, M.: Reinforcement learning. Adapt. Learn. Optim. 12(3) (2012)","DOI":"10.1007\/978-3-642-27645-3_1"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"James, S., et al.: Sim-to-real via sim-to-sim: Data-efficient robotic grasping via randomized-to-canonical adaptation networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12627\u201312637 (2019)","DOI":"10.1109\/CVPR.2019.01291"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89098-8_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T10:45:35Z","timestamp":1634467535000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89098-8_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030890971","9783030890988"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89098-8_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"18 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Yantai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"22 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2021.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}