{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T17:14:43Z","timestamp":1784826883226,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,21]]},"DOI":"10.1145\/3820709.3820741","type":"proceedings-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T16:58:41Z","timestamp":1784825921000},"page":"135-143","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Future-Aware Reinforcement Learning for Precision Assembly via LSTM-Based Trajectory Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5505-6554","authenticated-orcid":false,"given":"Mohamed","family":"Maarouf","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Tsinghua University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6324-6505","authenticated-orcid":false,"given":"ZhuFeng","family":"Shao","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Tsinghua University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9973-148X","authenticated-orcid":false,"given":"Ming","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Tsinghua University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5496-5558","authenticated-orcid":false,"given":"Xiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Mechanical Engineering, Tsinghua University, Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"e_1_3_3_1_1_2","unstructured":"Inoue T. Giovanni D. M. Munawar A. Yokoya T. & Tachibana R. (2017 August 14). Deep reinforcement learning for high precision assembly tasks. arXiv.org. https:\/\/arxiv.org\/abs\/1708.04033"},{"key":"e_1_3_3_1_2_2","volume-title":"Taylor","author":"Lozano-P\u00e9rez Tomas","year":"1984","unstructured":"Tomas Lozano-P\u00e9rez, Matthew T. Mason, and Russell H. Taylor. 1984. Automatic synthesis of fine-motion strategies for robots. The International Journal of Robotics Research (IJRR)."},{"key":"e_1_3_3_1_3_2","article-title":"Quasi-static assembly of compliantly supported rigid parts","author":"Whitney Daniel E.","year":"1982","unstructured":"Daniel E. Whitney. 1982. Quasi-static assembly of compliantly supported rigid parts. Journal of Dynamic Systems, Measurement, and Control.","journal-title":"Journal of Dynamic Systems, Measurement, and Control."},{"key":"e_1_3_3_1_4_2","volume-title":"Mechanics of robotic manipulation","author":"M.","year":"2001","unstructured":"Mason, M. T. (2001). Mechanics of robotic manipulation. MIT Press."},{"key":"e_1_3_3_1_5_2","volume-title":"Proceedings of AAAI.","author":"Hausknecht Matthew","year":"2015","unstructured":"Matthew Hausknecht and Peter Stone. 2015. Deep recurrent Q-learning for partially observable MDPs. In Proceedings of AAAI."},{"key":"e_1_3_3_1_6_2","volume-title":"Proceedings of ICLR.","author":"Heess Nicolas","year":"2015","unstructured":"Nicolas Heess, Jonathan Hunt, Timothy Lillicrap, and David Silver. 2015. Memory-based control with recurrent neural networks. In Proceedings of ICLR."},{"key":"e_1_3_3_1_7_2","volume-title":"Planning and acting in partially observable stochastic domains. Artificial Intelligence","author":"Littman L. P.","year":"1998","unstructured":"Kaelbling, L. P., Littman, M. L., & Cassandra, A. R. (1998). Planning and acting in partially observable stochastic domains. Artificial Intelligence."},{"key":"e_1_3_3_1_8_2","volume-title":"Modern robotics: Mechanics, planning, and control","author":"K.","year":"2017","unstructured":"Lynch, K. M., & Park, F. C. (2017). Modern robotics: Mechanics, planning, and control. Cambridge University Press."},{"key":"e_1_3_3_1_9_2","unstructured":"Reinforcement Learning for Robotic Assembly with Force Control | EECS at UC Berkeley. (n.d.). https:\/\/www2.eecs.berkeley.edu\/Pubs\/TechRpts\/2020\/EECS-2020-20.html"},{"key":"e_1_3_3_1_10_2","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).","author":"Vecerik Mel","year":"2019","unstructured":"Mel Vecerik, Oleg Sushkov, David Barker, Todd Hester, Thomas Roth\u00f6rl, Jonathan Scholz, and Martin Riedmiller. 2019. A practical approach to insertion with variable socket position using deep reinforcement learning. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)."},{"key":"e_1_3_3_1_11_2","volume-title":"Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS).","author":"Schoettler Gerrit","year":"2020","unstructured":"Gerrit Schoettler, Ashvin Nair, Juan Aparicio Ojea, Sergey Levine, and Eugen Solowjow. 2020. Meta-reinforcement learning for robotic industrial insertion tasks. In Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)."},{"key":"e_1_3_3_1_12_2","volume-title":"IEEE International Conference on Robotics and Automation (ICRA).","author":"Agogino J. A.","year":"2019","unstructured":"Luo, J., Solowjow, E., Wen, C., Ojea, J. A., Agogino, A., Tamar, A., & Abbeel, P. (2019). Reinforcement learning on variable impedance controller for high-precision robotic assembly. IEEE International Conference on Robotics and Automation (ICRA)."},{"key":"e_1_3_3_1_13_2","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).","author":"Johannink Tobias","year":"2019","unstructured":"Tobias Johannink, Shikhar Bahl, Ashvin Nair, Jianlan Luo, Avinash Kumar, Matthias Loskyll, Juan Aparicio Ojea, Eugen Solowjow, and Sergey Levine. 2019. Residual reinforcement learning for robot control. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)."},{"key":"e_1_3_3_1_14_2","volume-title":"Michael Burke, Franziska Meier, Stefan Schaal, and Subramanian Ramamoorthy.","author":"Davchev Todor","year":"2021","unstructured":"Todor Davchev, Kevin Sebastian Luck, Michael Burke, Franziska Meier, Stefan Schaal, and Subramanian Ramamoorthy. 2021. Residual learning from demonstration for contact-rich manipulation. IEEE Robotics and Automation Letters (RA-L)."},{"key":"e_1_3_3_1_15_2","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).","author":"Wu Zheng","year":"2021","unstructured":"Zheng Wu, Wenzhao Lian, Vaibhav Unhelkar, Masayoshi Tomizuka, and Stefan Schaal. 2021. Learning dense rewards for contact-rich manipulation tasks. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)."},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Tang B. Lin M. A. Akinola I. Handa A. Sukhatme G. S. Ramos F. Fox D. & Narang Y. (2023 May 26). IndustReal: Transferring Contact-Rich Assembly Tasks from Simulation to Reality. arXiv.org. https:\/\/arxiv.org\/abs\/2305.17110","DOI":"10.15607\/RSS.2023.XIX.039"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural Computation.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_3_1_18_2","volume-title":"Proceedings of CVPR.","author":"Alahi Alexandre","year":"2016","unstructured":"Alexandre Alahi, Kratarth Goel, Vignesh Ramanathan, Alexandre Robicquet, Li Fei-Fei, and Silvio Savarese. 2016. Social LSTM: Human trajectory prediction in crowded spaces. In Proceedings of CVPR."},{"key":"e_1_3_3_1_19_2","volume-title":"Recurrent environment simulators. arXiv preprint arXiv:1704.02254","author":"S.","year":"2017","unstructured":"Chiappa, S., Racani\u00e8re, S., Wierstra, D., & Mohamed, S. (2017). Recurrent environment simulators. arXiv preprint arXiv:1704.02254."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Marougkas I. Ramesh D. M. Doerr J. H. Granados E. Sivaramakrishnan A. Boularias A. & Bekris K. E. (2025 May 17). Integrating model-based control and RL for Sim2Real transfer of tight insertion policies. arXiv.org. https:\/\/arxiv.org\/abs\/2505.11858","DOI":"10.1109\/ICRA55743.2025.11128860"},{"key":"e_1_3_3_1_21_2","volume-title":"Isaac Gym: High performance GPU-based physics simulation for robot learning. In NeurIPS Datasets and Benchmarks.","author":"Makoviychuk Viktor","year":"2021","unstructured":"Viktor Makoviychuk, Lukasz Wawrzyniak, Yunrong Guo, Michelle Lu, Kier Storey, Miles Macklin, David Hoeller, Nikita Rudin, Arthur Allshire, Ankur Handa, and Gavriel State. 2021. Isaac Gym: High performance GPU-based physics simulation for robot learning. In NeurIPS Datasets and Benchmarks."},{"key":"e_1_3_3_1_22_2","volume-title":"Learning to walk in minutes using massively parallel deep reinforcement learning. CoRL","author":"M.","year":"2021","unstructured":"Rudin, N., Hoeller, D., Reist, P., & Hutter, M. (2021). Learning to walk in minutes using massively parallel deep reinforcement learning. CoRL."},{"key":"e_1_3_3_1_23_2","volume-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271","author":"J.","year":"2018","unstructured":"Bai, S., Kolter, J. Z., & Koltun, V. (2018). An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271."},{"key":"e_1_3_3_1_24_2","volume-title":"Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850","author":"A.","year":"2013","unstructured":"Graves, A. (2013). Generating sequences with recurrent neural networks. arXiv preprint arXiv:1308.0850."},{"key":"e_1_3_3_1_25_2","volume-title":"Reinforcement learning of impedance policies for peg-in-hole tasks","author":"Kozlovsky Shir","unstructured":"Shir Kozlovsky, Elad Newman, and Miriam Zacksenhouse. 2022. Reinforcement learning of impedance policies for peg-in-hole tasks. IEEE Robotics and Automation Letters (RA-L)."},{"key":"e_1_3_3_1_26_2","unstructured":"Jing Xu Zhimin Hou Zhi Liu and Hong Qiao. 2019. A survey of robotic peg-in-hole assembly. arXiv preprint arXiv:1904.05240."},{"key":"e_1_3_3_1_27_2","article-title":"Assessing transferability from simulation to reality for reinforcement learning","author":"Muratore Fabio","year":"2019","unstructured":"Fabio Muratore, Michael Gienger, and Jan Peters. 2019. Assessing transferability from simulation to reality for reinforcement learning. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)."},{"key":"e_1_3_3_1_28_2","volume-title":"Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).","author":"Peng Xue Bin","year":"2018","unstructured":"Xue Bin Peng, Marcin Andrychowicz, Wojciech Zaremba, and Pieter Abbeel. 2018. Sim-to-real transfer of robotic control with dynamics randomization. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA)."},{"key":"e_1_3_3_1_29_2","volume-title":"Proceedings of Robotics: Science and Systems (RSS).","author":"Narang Yashraj","year":"2022","unstructured":"Yashraj Narang, Kier Storey, Iretiayo Akinola, Miles Macklin, Philipp Reist, Lukasz Wawrzyniak, Yunrong Guo, Adam Moravanszky, Gavriel State, and Michelle Lu. 2022. Factory: Fast contact for robotic assembly. In Proceedings of Robotics: Science and Systems (RSS)."},{"key":"e_1_3_3_1_30_2","volume-title":"Hidden parameter Markov decision processes: A semiparametric regression approach for discovering latent task parametrizations. IJCAI","author":"G.","year":"2016","unstructured":"Doshi-Velez, F., & Konidaris, G. (2016). Hidden parameter Markov decision processes: A semiparametric regression approach for discovering latent task parametrizations. IJCAI."},{"key":"e_1_3_3_1_31_2","volume-title":"Learning dexterous in-hand manipulation. The International Journal of Robotics Research","year":"2020","unstructured":"Andrychowicz, M., Baker, B., Chociej, M., J\u00f3zefowicz, R., McGrew, B., Petron, A., Plappert, M., Powell, G., Ray, A., Schneider, J., et al. (2020). Learning dexterous in-hand manipulation. The International Journal of Robotics Research."}],"event":{"name":"RobCE 2026: 2026 6th International Conference on Robotics and Control Engineering","location":"Hong Kong Hong Kong","acronym":"RobCE 2026"},"container-title":["Proceedings of the 6th International Conference on Robotics and Control Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3820709.3820741","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T17:00:01Z","timestamp":1784826001000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3820709.3820741"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":31,"alternative-id":["10.1145\/3820709.3820741","10.1145\/3820709"],"URL":"https:\/\/doi.org\/10.1145\/3820709.3820741","relation":{},"subject":[],"published":{"date-parts":[[2026,5,21]]},"assertion":[{"value":"2026-07-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}